{"generated_at":"2026-10-16T13:28:10.769Z","counts":{"live":624,"pending":971,"authors":215,"media":138},"models":[{"id":"allenai/olmo-3.1-32b-instruct","author":"allenai","name":"Olmo 3.1 32B Instruct","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.2,"output_per_m":0.6,"unit":null,"unit_price":null,"highlights":[]},{"id":"allenai/olmocr-2","author":"allenai","name":"Olmocr 2","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.14,"output_per_m":0.8,"unit":null,"unit_price":null,"highlights":[]},{"id":"allenai/olmocr-2-7b-1025","author":"allenai","name":"Olmocr 2 7B 1025","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.09,"output_per_m":0.19,"unit":null,"unit_price":null,"variants":["free"],"highlights":[]},{"id":"allenai/olmocr-7b-0725-fp8","author":"allenai","name":"Olmocr 7B 0725 FP8","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.27,"output_per_m":1.5,"unit":null,"unit_price":null,"highlights":[]},{"id":"allenai/olmocr-7b-0825","author":"allenai","name":"Olmocr 7B 0825","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.14,"output_per_m":0.8,"unit":null,"unit_price":null,"highlights":[]},{"id":"allenai/olmocr-7b-1025","author":"allenai","name":"Olmocr 7B 1025","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.14,"output_per_m":0.8,"unit":null,"unit_price":null,"highlights":[]},{"id":"anthropic/claude-fable-5","author":"anthropic","name":"Claude Fable 5","provider":"anthropic","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":10,"output_per_m":50,"unit":null,"unit_price":null,"created":1780790400,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"Claude model for creative writing, analysis, and controlled agent workflows","highlights":["Vision","Reasoning","Tools"]},{"id":"anthropic/claude-fable-5-1","author":"anthropic","name":"Claude Fable 5.1","provider":"anthropic","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":10,"output_per_m":50,"unit":null,"unit_price":null,"created":1788220800,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"Claude model for demanding reasoning and long-horizon agentic work","highlights":["Vision","Reasoning","Tools"]},{"id":"anthropic/claude-haiku-4-5","author":"anthropic","name":"Claude Haiku 4.5 (latest)","provider":"anthropic","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":200000,"input_per_m":1,"output_per_m":5,"unit":null,"unit_price":null,"created":1760486400,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":64000,"description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","highlights":["Fastest","Vision","Reasoning","Tools"]},{"id":"anthropic/claude-haiku-4-5-20251001","author":"anthropic","name":"Claude Haiku 4.5 (latest)","provider":"anthropic","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":200000,"input_per_m":1,"output_per_m":5,"unit":null,"unit_price":null,"created":1760486400,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":64000,"description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","highlights":["Vision","Reasoning","Tools"]},{"id":"anthropic/claude-haiku-5-5","author":"anthropic","name":"Claude Haiku 5.5","provider":"anthropic","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":0.1,"output_per_m":0.5,"unit":null,"unit_price":null,"created":1791331200,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"Fast Claude model for responsive assistance, classification, and lightweight agents","highlights":["Vision","Reasoning","Tools"]},{"id":"anthropic/claude-opus-4-5","author":"anthropic","name":"Claude Opus 4.5 (latest)","provider":"anthropic","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":200000,"input_per_m":5,"output_per_m":25,"unit":null,"unit_price":null,"created":1763942400,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":64000,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","highlights":["Vision","Reasoning","Tools"]},{"id":"anthropic/claude-opus-4-5-20251101","author":"anthropic","name":"Claude Opus 4.5 (latest)","provider":"anthropic","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":200000,"input_per_m":5,"output_per_m":25,"unit":null,"unit_price":null,"created":1763942400,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":64000,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","highlights":["Vision","Reasoning","Tools"]},{"id":"anthropic/claude-opus-4-6","author":"anthropic","name":"Claude Opus 4.6","provider":"anthropic","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":5,"output_per_m":25,"unit":null,"unit_price":null,"created":1770163200,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"High-end Claude for difficult coding, planning, and slower expert reasoning","highlights":["Vision","Reasoning","Tools"]},{"id":"anthropic/claude-opus-4-7","author":"anthropic","name":"Claude Opus 4.7","provider":"anthropic","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":5,"output_per_m":25,"unit":null,"unit_price":null,"created":1776124800,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"Stronger Opus tier for advanced software work and high-stakes reasoning","highlights":["Vision","Reasoning","Tools"]},{"id":"anthropic/claude-opus-4-8","author":"anthropic","name":"Claude Opus 4.8","provider":"anthropic","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":5,"output_per_m":25,"unit":null,"unit_price":null,"created":1779926400,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","highlights":["Vision","Reasoning","Tools"]},{"id":"anthropic/claude-opus-5","author":"anthropic","name":"Claude Opus 5","provider":"anthropic","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":5,"output_per_m":25,"unit":null,"unit_price":null,"created":1784851200,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"Strongest Claude Opus model for coding, agents, and professional work","highlights":["Vision","Reasoning","Tools"]},{"id":"anthropic/claude-opus-5-5","author":"anthropic","name":"Claude Opus 5.5","provider":"anthropic","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":4,"output_per_m":20,"unit":null,"unit_price":null,"created":1790035200,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"Claude model for long-running agentic coding and knowledge work","highlights":["Vision","Reasoning","Tools"]},{"id":"anthropic/claude-sonnet-4-5","author":"anthropic","name":"Claude Sonnet 4.5 (latest)","provider":"anthropic","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":200000,"input_per_m":3,"output_per_m":15,"unit":null,"unit_price":null,"created":1759104000,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":64000,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","highlights":["Vision","Reasoning","Tools"]},{"id":"anthropic/claude-sonnet-4-5-20250929","author":"anthropic","name":"Claude Sonnet 4.5 (latest)","provider":"anthropic","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":200000,"input_per_m":3,"output_per_m":15,"unit":null,"unit_price":null,"created":1759104000,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":64000,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","highlights":["Vision","Reasoning","Tools"]},{"id":"anthropic/claude-sonnet-4-6","author":"anthropic","name":"Claude Sonnet 4.6","provider":"anthropic","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":3,"output_per_m":15,"unit":null,"unit_price":null,"created":1771286400,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"Claude workhorse for coding agents, careful analysis, and production cost control","highlights":["Vision","Reasoning","Tools"]},{"id":"anthropic/claude-sonnet-5","author":"anthropic","name":"Claude Sonnet 5","provider":"anthropic","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":2,"output_per_m":10,"unit":null,"unit_price":null,"created":1782691200,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"Everyday Claude agent model for coding, planning, browsing, and general work","highlights":["Fastest","Vision","Reasoning","Tools"]},{"id":"anthropic/claude-sonnet-5-5","author":"anthropic","name":"Claude Sonnet 5.5","provider":"anthropic","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":2,"output_per_m":10,"unit":null,"unit_price":null,"created":1790553600,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"Fast Claude model for everyday coding, agents, and knowledge work","highlights":["Vision","Reasoning","Tools"]},{"id":"arize-ai/qwen-2-1.5b-instruct","author":"arize-ai","name":"Qwen 2 1.5B Instruct","provider":"together","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.1,"output_per_m":0.1,"unit":null,"unit_price":null,"highlights":[]},{"id":"austism/chronos-hermes-13b-v2","author":"austism","name":"Chronos Hermes 13B V2","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.13,"output_per_m":0.13,"unit":null,"unit_price":null,"variants":["free"],"highlights":[]},{"id":"baai/bge-base-en-v1.5","author":"baai","name":"Bge Base En V1.5","provider":"deepinfra","status":"live","blocked_by":null,"kind":"embedding","free_kind":null,"context":null,"input_per_m":0.005,"output_per_m":null,"unit":null,"unit_price":null,"highlights":[]},{"id":"baai/bge-en-icl","author":"baai","name":"Bge En Icl","provider":"deepinfra","status":"live","blocked_by":null,"kind":"embedding","free_kind":null,"context":null,"input_per_m":0.01,"output_per_m":null,"unit":null,"unit_price":null,"highlights":[]},{"id":"baai/bge-large-en-v1.5","author":"baai","name":"Bge Large En V1.5","provider":"deepinfra","status":"live","blocked_by":null,"kind":"embedding","free_kind":null,"context":null,"input_per_m":0.01,"output_per_m":null,"unit":null,"unit_price":null,"highlights":[]},{"id":"baai/bge-m3","author":"baai","name":"BGE M3","provider":"deepinfra","status":"live","blocked_by":null,"kind":"embedding","free_kind":null,"context":8192,"input_per_m":0.01,"output_per_m":null,"unit":null,"unit_price":null,"created":1706572800,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":0,"description":"Multilingual embedding model combining dense, sparse, and multi-vector retrieval","highlights":[]},{"id":"baai/bge-m3-multi","author":"baai","name":"Bge M3 Multi","provider":"deepinfra","status":"live","blocked_by":null,"kind":"embedding","free_kind":null,"context":null,"input_per_m":0.01,"output_per_m":null,"unit":null,"unit_price":null,"highlights":[]},{"id":"bigcode/starcoder2-15b-instruct-v0.1","author":"bigcode","name":"Starcoder2 15B Instruct V0.1","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.15,"output_per_m":0.15,"unit":null,"unit_price":null,"variants":["free"],"highlights":[]},{"id":"cognitivecomputations/dolphin-2.6-mixtral-8x7b","author":"cognitivecomputations","name":"Dolphin 2.6 Mixtral 8X7B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.24,"output_per_m":0.24,"unit":null,"unit_price":null,"highlights":[]},{"id":"cognitivecomputations/dolphin-2.9.1-llama-3-70b","author":"cognitivecomputations","name":"Dolphin 2.9.1 Llama 3 70B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.35,"output_per_m":0.4,"unit":null,"unit_price":null,"highlights":[]},{"id":"deepinfra/airoboros-70b","author":"deepinfra","name":"Airoboros 70B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.7,"output_per_m":0.9,"unit":null,"unit_price":null,"highlights":[]},{"id":"deepinfra/bytedance/seed-1.8","author":"deepinfra","name":"Seed 1.8","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":256000,"input_per_m":0.25,"output_per_m":2,"unit":null,"unit_price":null,"created":1756684800,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":32768,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","highlights":["Vision","Reasoning","Tools"]},{"id":"deepinfra/bytedance/seed-2.0-code","author":"deepinfra","name":"Seed 2.0 Code","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":256000,"input_per_m":0.5,"output_per_m":3,"unit":null,"unit_price":null,"created":1771027200,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"ByteDance Seed coding model for multimodal software engineering and long-running agents","highlights":["Vision","Reasoning","Tools"]},{"id":"deepinfra/bytedance/seed-2.0-mini","author":"deepinfra","name":"Seed 2.0 Mini","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":256000,"input_per_m":0.1,"output_per_m":0.4,"unit":null,"unit_price":null,"created":1771027200,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":32000,"description":"Lightweight ByteDance Seed 2.0 model for low-latency multimodal reasoning and high-volume tasks","highlights":["Vision","Reasoning","Tools"]},{"id":"deepinfra/bytedance/seed-2.0-pro","author":"deepinfra","name":"Seed 2.0 Pro","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":256000,"input_per_m":0.5,"output_per_m":3,"unit":null,"unit_price":null,"created":1771027200,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"Flagship ByteDance Seed 2.0 model for complex multimodal reasoning and long-horizon agent workflows","highlights":["Vision","Reasoning","Tools"]},{"id":"deepinfra/deepseek-ai/deepseek-v4-flash-vision-exp","author":"deepinfra","name":"DeepSeek V4 Flash Vision Exp","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":0.44,"output_per_m":1.32,"unit":null,"unit_price":null,"created":1788998400,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":393216,"description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","highlights":["Vision","Reasoning","Tools"]},{"id":"deepinfra/deepseek-ai/deepseek-v4.1-flash","author":"deepinfra","name":"DeepSeek V4.1 Flash","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":0.2,"output_per_m":0.6,"unit":null,"unit_price":null,"created":1788998400,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":384000,"description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","highlights":["Vision","Reasoning","Tools"]},{"id":"deepinfra/google/gemini-2.5-flash","author":"deepinfra","name":"Gemini 2.5 Flash","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1048576,"input_per_m":0.3,"output_per_m":2.5,"unit":null,"unit_price":null,"created":1750118400,"variant":"thinking","reasoning":true,"input_modalities":["text","image","audio","video","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":true},"max_output":65536,"description":"Fast Gemini workhorse for multimodal apps where latency and price matter","highlights":["Vision","Reasoning","Tools"]},{"id":"deepinfra/google/gemini-2.5-pro","author":"deepinfra","name":"Gemini 2.5 Pro","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1048576,"input_per_m":1.25,"output_per_m":10,"unit":null,"unit_price":null,"created":1750118400,"variant":"thinking","reasoning":true,"input_modalities":["text","image","audio","video","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":true},"max_output":65536,"description":"Google's proven reasoning model for coding, math, and multimodal analysis","highlights":["Vision","Reasoning","Tools"]},{"id":"deepinfra/google/gemini-3.1-pro","author":"deepinfra","name":"Gemini 3.1 Pro Preview","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1048576,"input_per_m":2,"output_per_m":12,"unit":null,"unit_price":null,"created":1771459200,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":true},"max_output":65536,"description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","highlights":["Vision","Reasoning","Tools"]},{"id":"deepinfra/google/gemma-4-31b-it-ultra","author":"deepinfra","name":"Gemma 4 31B It Ultra","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.27,"output_per_m":0.76,"unit":null,"unit_price":null,"highlights":[]},{"id":"deepinfra/ibm-granite/granite-4.2-8b","author":"deepinfra","name":"Granite 4.2 8B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.06,"output_per_m":0.25,"unit":null,"unit_price":null,"variants":["free"],"created":1788134400,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":false,"audio":false},"max_output":117964,"description":"Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,...","highlights":["Reasoning","Tools"]},{"id":"deepinfra/inclusionai/ling-3.0-flash-vl","author":"deepinfra","name":"Ling 3.0 Flash VL","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.06,"output_per_m":0.18,"unit":null,"unit_price":null,"variants":["free"],"created":1788998400,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":32768,"description":"Native multimodal hybrid MoE model for image and video understanding, reasoning, and visual agents","highlights":["Vision","Reasoning","Tools"]},{"id":"deepinfra/inclusionai/ling-3.1-flash","author":"deepinfra","name":"Ling 3.1 Flash","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.3,"output_per_m":0.9,"unit":null,"unit_price":null,"created":1790640000,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":false,"audio":false},"max_output":32768,"description":"Efficient model for low-latency assistance, extraction, and routine automation","highlights":["Reasoning","Tools"]},{"id":"deepinfra/meta-llama/llama-3.3-70b-instruct-turbo","author":"deepinfra","name":"Llama 3.3 70B Turbo","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.1,"output_per_m":0.32,"unit":null,"unit_price":null,"created":1733443200,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":false,"vision":false,"audio":false},"max_output":16384,"description":"Compact Llama instruction model for fast chat and local deployment","highlights":["Tools"]},{"id":"deepinfra/nvidia/nvidia-nemotron-3.5-super-vl","author":"deepinfra","name":"Nvidia Nemotron 3.5 Super VL","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.2,"output_per_m":1,"unit":null,"unit_price":null,"highlights":[]},{"id":"deepinfra/openai/gpt-oss-120b-ultra","author":"deepinfra","name":"GPT OSS 120B Ultra","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.2,"output_per_m":0.95,"unit":null,"unit_price":null,"highlights":[]},{"id":"deepinfra/qwen/qwen3.8-flash","author":"deepinfra","name":"Qwen3.8 Flash","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":0.113,"output_per_m":0.382,"unit":null,"unit_price":null,"created":1787702400,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":131072,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","highlights":["Vision","Reasoning","Tools"]},{"id":"deepinfra/qwen/qwen3.8-max","author":"deepinfra","name":"Qwen3.8 Max","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":1.65,"output_per_m":4.951,"unit":null,"unit_price":null,"created":1785715200,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":131072,"description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","highlights":["Vision","Reasoning","Tools"]},{"id":"deepinfra/stepfun-ai/step-5-preview","author":"deepinfra","name":"Step 5 Preview","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":1,"output_per_m":2.7,"unit":null,"unit_price":null,"created":1789516800,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":65536,"description":"StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window","highlights":["Vision","Reasoning","Tools"]},{"id":"deepinfra/tencent/hy4-preview","author":"deepinfra","name":"Hy4 preview","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1024000,"input_per_m":0.834,"output_per_m":2.501,"unit":null,"unit_price":null,"created":1787875200,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":64000,"description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","highlights":["Reasoning","Tools"]},{"id":"deepinfra/xiaomimimo/mimo-v2.6-flash","author":"deepinfra","name":"MiMo-V2.6-Flash","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1048576,"input_per_m":0.14,"output_per_m":0.28,"unit":null,"unit_price":null,"created":1790035200,"variant":"thinking","reasoning":true,"input_modalities":["text","image","audio","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":true},"max_output":131072,"description":"MiMo Flash model for multimodal coding agents and long-context automation","highlights":["Vision","Reasoning","Tools"]},{"id":"deepinfra/xiaomimimo/mimo-v2.6-pro","author":"deepinfra","name":"MiMo-V2.6-Pro","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1048576,"input_per_m":0.43,"output_per_m":0.87,"unit":null,"unit_price":null,"created":1790035200,"variant":"thinking","reasoning":true,"input_modalities":["text","image","audio","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":true},"max_output":131072,"description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","highlights":["Vision","Reasoning","Tools"]},{"id":"deepreinforce-ai/ornith-1.0-35b","author":"deepreinforce-ai","name":"Ornith 1.0 35B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.1,"output_per_m":0.75,"unit":null,"unit_price":null,"highlights":[]},{"id":"deepseek-ai/deepseek-ocr","author":"deepseek-ai","name":"DeepSeek OCR","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":8192,"input_per_m":0.03,"output_per_m":0.1,"unit":null,"unit_price":null,"variants":["free"],"created":1760918400,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":8192,"description":"OCR model for extracting structured text from documents and screenshots","highlights":["Vision"]},{"id":"deepseek-ai/deepseek-prover-v2-671b","author":"deepseek-ai","name":"DeepSeek Prover V2 671B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.5,"output_per_m":2.18,"unit":null,"unit_price":null,"highlights":[]},{"id":"deepseek-ai/deepseek-r1-0528-turbo","author":"deepseek-ai","name":"DeepSeek R1 0528 Turbo","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":1,"output_per_m":3,"unit":null,"unit_price":null,"highlights":[]},{"id":"deepseek-ai/deepseek-r1-distill-qwen-32b","author":"deepseek-ai","name":"DeepSeek R1 Distill Qwen 32B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":32768,"input_per_m":0.27,"output_per_m":0.27,"unit":null,"unit_price":null,"created":1735689600,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":16384,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","highlights":["Reasoning","Tools"]},{"id":"deepseek-ai/deepseek-r1-distill-qwen-32b:free","author":"deepseek-ai","name":"DeepSeek R1 Distill Qwen 32B (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":32768,"input_per_m":0,"output_per_m":0,"unit":null,"unit_price":null,"variants":["free"],"created":1735689600,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":16384,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","highlights":["Free","Reasoning","Tools"]},{"id":"deepseek-ai/deepseek-r1-turbo","author":"deepseek-ai","name":"DeepSeek R1 (Turbo)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":64000,"input_per_m":1,"output_per_m":3,"unit":null,"unit_price":null,"created":1737331200,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":false,"audio":false},"max_output":16000,"description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","highlights":["Reasoning","Tools"]},{"id":"deepseek-ai/deepseek-v3","author":"deepseek-ai","name":"DeepSeek V3","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":164000,"input_per_m":0.32,"output_per_m":0.89,"unit":null,"unit_price":null,"created":1735171200,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":false,"vision":false,"audio":false},"max_output":164000,"description":"DeepSeek chat model for instruction following, coding, and analysis","highlights":["Tools"]},{"id":"deepseek-ai/deepseek-v3-0324","author":"deepseek-ai","name":"DeepSeek Chat 0324","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":128000,"input_per_m":0.24,"output_per_m":0.9,"unit":null,"unit_price":null,"created":1742774400,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":false,"vision":false,"audio":false},"max_output":8192,"description":"March 2025 checkpoint of DeepSeek-V3 with improved reasoning and coding","highlights":["Tools"]},{"id":"deepseek-ai/deepseek-v3-0324-turbo","author":"deepseek-ai","name":"DeepSeek V3 0324 Turbo","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":1,"output_per_m":3,"unit":null,"unit_price":null,"highlights":[]},{"id":"deepseek-ai/deepseek-v3.1","author":"deepseek-ai","name":"DeepSeek-V3.1","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.25,"output_per_m":0.95,"unit":null,"unit_price":null,"created":1755734400,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":8192,"description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes","highlights":["Reasoning","Tools"]},{"id":"deepseek/deepseek-r1","author":"deepseek","name":"DeepSeek R1","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":128000,"input_per_m":0.7,"output_per_m":2.4,"unit":null,"unit_price":null,"created":1737331200,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":8192,"description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","highlights":["Reasoning","Tools"]},{"id":"deepseek/deepseek-r1-0528","author":"deepseek","name":"DeepSeek-R1-0528","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":163840,"input_per_m":0.5,"output_per_m":2.15,"unit":null,"unit_price":null,"created":1748390400,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":false,"audio":false},"max_output":64000,"description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","highlights":["Reasoning","Tools"]},{"id":"deepseek/deepseek-r1-distill-llama-70b","author":"deepseek","name":"DeepSeek R1 Distill Llama 70B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.7,"output_per_m":0.8,"unit":null,"unit_price":null,"created":1737590400,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":131072,"description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","highlights":["Reasoning"]},{"id":"deepseek/deepseek-v3.1-terminus","author":"deepseek","name":"DeepSeek V3.1 Terminus","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":128000,"input_per_m":0.27,"output_per_m":0.95,"unit":null,"unit_price":null,"created":1754092800,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":false,"vision":false,"audio":false},"max_output":65536,"description":"DeepSeek chat model for instruction following, coding, and analysis","highlights":["Tools"]},{"id":"deepseek/deepseek-v3.2","author":"deepseek","name":"DeepSeek V3.2","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":163840,"input_per_m":0.26,"output_per_m":0.38,"unit":null,"unit_price":null,"created":1753142400,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":163840,"description":"DeepSeek chat model for instruction following, coding, and analysis","highlights":["Tools"]},{"id":"deepseek/deepseek-v4-flash","author":"deepseek","name":"DeepSeek V4 Flash","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":0.09,"output_per_m":0.18,"unit":null,"unit_price":null,"variants":["free"],"created":1776988800,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":false,"audio":false},"max_output":384000,"description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","highlights":["Reasoning","Tools"]},{"id":"deepseek/deepseek-v4-flash-0731","author":"deepseek","name":"DeepSeek V4 Flash 0731","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1048576,"input_per_m":0.06,"output_per_m":0.18,"unit":null,"unit_price":null,"variants":["free"],"created":1785456000,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":false,"audio":false},"max_output":943718,"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","highlights":["Reasoning","Tools"]},{"id":"deepseek/deepseek-v4-pro","author":"deepseek","name":"DeepSeek V4 Pro","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":1.3,"output_per_m":2.6,"unit":null,"unit_price":null,"created":1786492800,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":false,"audio":false},"max_output":393216,"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","highlights":["Reasoning","Tools"]},{"id":"deepseek/deepseek-v4-pro-0813","author":"deepseek","name":"DeepSeek V4 Pro (0813)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":1.3,"output_per_m":2.6,"unit":null,"unit_price":null,"created":1786492800,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":false,"audio":false},"max_output":131072,"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","highlights":["Reasoning","Tools"]},{"id":"google/codegemma-7b-it","author":"google","name":"CodeGemma 7B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.07,"output_per_m":0.07,"unit":null,"unit_price":null,"variants":["free"],"highlights":[]},{"id":"google/codegemma-7b-it:free","author":"google","name":"CodeGemma 7B (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":null,"input_per_m":0,"output_per_m":0,"unit":null,"unit_price":null,"variants":["free"],"highlights":["Free"]},{"id":"google/embeddinggemma-300m","author":"google","name":"Embeddinggemma 300M","provider":"deepinfra","status":"live","blocked_by":null,"kind":"embedding","free_kind":null,"context":null,"input_per_m":0.002,"output_per_m":null,"unit":null,"unit_price":null,"highlights":[]},{"id":"google/gemini-3-flash-preview","author":"google","name":"Gemini 3 Flash Preview","provider":"google","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1048576,"input_per_m":0.5,"output_per_m":3,"unit":null,"unit_price":null,"created":1765929600,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":true},"max_output":65536,"description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","highlights":["Vision","Reasoning","Tools"]},{"id":"google/gemini-3.1-flash-lite","author":"google","name":"Gemini 3.1 Flash Lite Preview","provider":"google","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1048576,"input_per_m":0.25,"output_per_m":1.5,"unit":null,"unit_price":null,"created":1772496000,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":true},"max_output":65536,"description":"Legacy model retained for compatibility with older integrations","highlights":["Vision","Reasoning","Tools"]},{"id":"google/gemini-3.1-flash-lite-preview","author":"google","name":"Gemini 3.1 Flash Lite Preview","provider":"google","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1048576,"input_per_m":0.25,"output_per_m":1.5,"unit":null,"unit_price":null,"created":1772496000,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":true},"max_output":65536,"description":"Legacy model retained for compatibility with older integrations","highlights":["Vision","Reasoning","Tools"]},{"id":"google/gemini-3.1-pro-preview","author":"google","name":"Gemini 3.1 Pro Preview","provider":"google","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1048576,"input_per_m":2,"output_per_m":12,"unit":null,"unit_price":null,"created":1771459200,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":true},"max_output":65536,"description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","highlights":["Vision","Reasoning","Tools"]},{"id":"google/gemini-3.1-pro-preview-customtools","author":"google","name":"Gemini 3.1 Pro Preview Custom Tools","provider":"google","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1048576,"input_per_m":2,"output_per_m":12,"unit":null,"unit_price":null,"created":1771459200,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":true},"max_output":65536,"description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","highlights":["Vision","Reasoning","Tools"]},{"id":"google/gemini-3.5-flash","author":"google","name":"Gemini 3.5 Flash","provider":"google","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1048576,"input_per_m":1.5,"output_per_m":9,"unit":null,"unit_price":null,"created":1779148800,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":true},"max_output":65536,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","highlights":["Vision","Reasoning","Tools"]},{"id":"google/gemini-3.5-flash-lite","author":"google","name":"Gemini 3.5 Flash Lite","provider":"google","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1048576,"input_per_m":0.3,"output_per_m":2.5,"unit":null,"unit_price":null,"created":1784592000,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":true},"max_output":65536,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","highlights":["Fastest","Vision","Reasoning","Tools"]},{"id":"google/gemini-3.6-flash","author":"google","name":"Gemini 3.6 Flash","provider":"google","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1048576,"input_per_m":0.75,"output_per_m":3.75,"unit":null,"unit_price":null,"created":1784592000,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":true},"max_output":65536,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","highlights":["Fastest","Vision","Reasoning","Tools"]},{"id":"google/gemini-3.7-flash","author":"google","name":"Gemini 3.7 Flash","provider":"google","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1048576,"input_per_m":0.375,"output_per_m":1.875,"unit":null,"unit_price":null,"created":1786579200,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":true},"max_output":65536,"description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","highlights":["Vision","Reasoning","Tools"]},{"id":"google/gemini-4-argon","author":"google","name":"Gemini 4 Argon","provider":"google","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1048576,"input_per_m":4,"output_per_m":20,"unit":null,"unit_price":null,"created":1791849600,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":true},"max_output":32768,"description":"Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents","highlights":["Vision","Reasoning","Tools"]},{"id":"google/gemini-embedding-001","author":"google","name":"Gemini Embedding 001","provider":"google","status":"live","blocked_by":null,"kind":"embedding","free_kind":null,"context":2048,"input_per_m":0.15,"output_per_m":null,"unit":null,"unit_price":null,"created":1747699200,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":1,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","highlights":[]},{"id":"google/gemini-flash-latest","author":"google","name":"Gemini Flash Latest","provider":"google","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1048576,"input_per_m":0.375,"output_per_m":1.875,"unit":null,"unit_price":null,"created":1786579200,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":true},"max_output":65536,"description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","highlights":["Vision","Reasoning","Tools"]},{"id":"google/gemini-flash-lite-latest","author":"google","name":"Gemini Flash-Lite Latest","provider":"google","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1048576,"input_per_m":0.3,"output_per_m":2.5,"unit":null,"unit_price":null,"created":1784592000,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":true},"max_output":65536,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","highlights":["Vision","Reasoning","Tools"]},{"id":"google/gemini-pro-latest","author":"google","name":"Gemini Pro Latest","provider":"google","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1048576,"input_per_m":2,"output_per_m":12,"unit":null,"unit_price":null,"created":1774742400,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":true},"max_output":65536,"description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","highlights":["Vision","Reasoning","Tools"]},{"id":"google/gemma-1.1-7b-it","author":"google","name":"Gemma 1.1 7B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.07,"output_per_m":0.07,"unit":null,"unit_price":null,"variants":["free"],"highlights":[]},{"id":"google/gemma-1.1-7b-it:free","author":"google","name":"Gemma 1.1 7B (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":null,"input_per_m":0,"output_per_m":0,"unit":null,"unit_price":null,"variants":["free"],"highlights":["Free"]},{"id":"google/gemma-2-27b-it","author":"google","name":"Gemma 2 27B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":8192,"input_per_m":0.27,"output_per_m":0.27,"unit":null,"unit_price":null,"created":1720828800,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":true,"reasoning":false,"vision":false,"audio":false},"max_output":2048,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","highlights":[]},{"id":"google/gemma-2-27b-it:free","author":"google","name":"Gemma 2 27B (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":8192,"input_per_m":0,"output_per_m":0,"unit":null,"unit_price":null,"variants":["free"],"created":1720828800,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":true,"reasoning":false,"vision":false,"audio":false},"max_output":2048,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","highlights":["Free"]},{"id":"google/gemma-2-9b-it","author":"google","name":"Gemma 2 9B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.03,"output_per_m":0.06,"unit":null,"unit_price":null,"variants":["free"],"highlights":[]},{"id":"google/gemma-2-9b-it:free","author":"google","name":"Gemma 2 9B (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":null,"input_per_m":0,"output_per_m":0,"unit":null,"unit_price":null,"variants":["free"],"highlights":["Free"]},{"id":"google/gemma-3-12b-it","author":"google","name":"Gemma 3 12B IT","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.05,"output_per_m":0.15,"unit":null,"unit_price":null,"variants":["free"],"created":1741737600,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":false,"vision":true,"audio":false},"max_output":16384,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","highlights":["Vision","Tools"]},{"id":"google/gemma-3-27b-it","author":"google","name":"Gemma 3 27B IT","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.08,"output_per_m":0.16,"unit":null,"unit_price":null,"variants":["free"],"created":1741737600,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":false,"vision":true,"audio":false},"max_output":131072,"description":"Largest open Gemma 3 instruction model for multilingual text generation and visual understanding","highlights":["Vision","Tools"]},{"id":"google/gemma-3-4b-it","author":"google","name":"Gemma 3 4B IT","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.05,"output_per_m":0.1,"unit":null,"unit_price":null,"variants":["free"],"created":1741737600,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":false,"json":true,"reasoning":false,"vision":true,"audio":false},"max_output":16384,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","highlights":["Vision"]},{"id":"google/gemma-3-4b-it:free","author":"google","name":"Gemma 3 4B IT (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":131072,"input_per_m":0.05,"output_per_m":0.1,"unit":null,"unit_price":null,"variants":["free"],"created":1741737600,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":false,"json":true,"reasoning":false,"vision":true,"audio":false},"max_output":16384,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","highlights":["Free","Vision"]},{"id":"google/gemma-4-26b-a4b-it","author":"google","name":"Gemma 4 26B A4B IT","provider":"google","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.07,"output_per_m":0.34,"unit":null,"unit_price":null,"created":1775088000,"variant":"thinking","reasoning":true,"input_modalities":["image","text","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":235929,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","highlights":["Vision","Reasoning","Tools"]},{"id":"google/gemma-4-26b-a4b-it:free","author":"google","name":"Gemma 4 26B A4B IT (free)","provider":"google","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":262144,"input_per_m":0,"output_per_m":0,"unit":null,"unit_price":null,"variants":["free"],"created":1775088000,"variant":"thinking","reasoning":true,"input_modalities":["image","text","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":235929,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","highlights":["Free","Vision","Reasoning","Tools"]},{"id":"google/gemma-4-31b-it-turbo","author":"google","name":"Gemma 4 31B It Turbo","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.09,"output_per_m":0.34,"unit":null,"unit_price":null,"highlights":[]},{"id":"google/gemma-4-31b-it:free","author":"google","name":"Gemma 4 31B (free)","provider":"google","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":262144,"input_per_m":0,"output_per_m":0,"unit":null,"unit_price":null,"variants":["free"],"created":1775088000,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":131072,"description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","highlights":["Free","Vision","Reasoning","Tools"]},{"id":"google/gemma-4-e4b-it","author":"google","name":"Gemma 4 E4B IT","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.02,"output_per_m":0.1,"unit":null,"unit_price":null,"variants":["free"],"created":1775088000,"variant":"thinking","reasoning":true,"input_modalities":["text","image","audio"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":true},"max_output":8192,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","highlights":["Vision","Reasoning","Tools"]},{"id":"google/gemma-4-e4b-it:free","author":"google","name":"Gemma 4 E4B IT (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":131072,"input_per_m":0,"output_per_m":0,"unit":null,"unit_price":null,"variants":["free"],"created":1775088000,"variant":"thinking","reasoning":true,"input_modalities":["text","image","audio"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":true},"max_output":8192,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","highlights":["Free","Vision","Reasoning","Tools"]},{"id":"google/nano-banana-pro-preview","author":"google","name":"Nano-Banana-Pro","provider":"google","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":65536,"input_per_m":2,"output_per_m":12,"unit":null,"unit_price":null,"created":1763510400,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["image"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":0,"description":"Image model for prompt-driven generation, editing, and visual design workflows","highlights":["Vision","Tools"]},{"id":"gryphe/mythomax-l2-13b","author":"gryphe","name":"MythoMax 13B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":4096,"input_per_m":0.4,"output_per_m":0.4,"unit":null,"unit_price":null,"created":1688256000,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":true,"reasoning":false,"vision":false,"audio":false},"max_output":3686,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","highlights":[]},{"id":"gryphe/mythomax-l2-13b-turbo","author":"gryphe","name":"MythoMax L2 13B Turbo","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.13,"output_per_m":0.13,"unit":null,"unit_price":null,"variants":["free"],"highlights":[]},{"id":"inclusionai/ling-3.0-flash","author":"inclusionai","name":"Ling 3.0 Flash","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.06,"output_per_m":0.18,"unit":null,"unit_price":null,"variants":["free"],"created":1784764800,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":32768,"description":"Efficient model for low-latency assistance, extraction, and routine automation","highlights":["Reasoning","Tools"]},{"id":"intfloat/e5-base-v2","author":"intfloat","name":"E5 Base V2","provider":"deepinfra","status":"live","blocked_by":null,"kind":"embedding","free_kind":null,"context":null,"input_per_m":0.005,"output_per_m":null,"unit":null,"unit_price":null,"highlights":[]},{"id":"intfloat/e5-large-v2","author":"intfloat","name":"E5 Large v2","provider":"deepinfra","status":"live","blocked_by":null,"kind":"embedding","free_kind":null,"context":512,"input_per_m":0.01,"output_per_m":null,"unit":null,"unit_price":null,"created":1684454400,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":1024,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","highlights":[]},{"id":"intfloat/multilingual-e5-large","author":"intfloat","name":"Multilingual E5 Large","provider":"deepinfra","status":"live","blocked_by":null,"kind":"embedding","free_kind":null,"context":null,"input_per_m":0.01,"output_per_m":null,"unit":null,"unit_price":null,"highlights":[]},{"id":"koboldai/llama2-13b-tiefighter","author":"koboldai","name":"Llama2 13B Tiefighter","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.1,"output_per_m":0.1,"unit":null,"unit_price":null,"variants":["free"],"highlights":[]},{"id":"lizpreciatior/lzlv_70b_fp16_hf","author":"lizpreciatior","name":"Lzlv 70B Fp16 Hf","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.35,"output_per_m":0.4,"unit":null,"unit_price":null,"highlights":[]},{"id":"mattshumer/reflection-llama-3.1-70b","author":"mattshumer","name":"Reflection Llama 3.1 70B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.35,"output_per_m":0.4,"unit":null,"unit_price":null,"highlights":[]},{"id":"meta-llama/llama-2-13b-chat-hf","author":"meta-llama","name":"Llama 2 13B Chat Hf","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.13,"output_per_m":0.13,"unit":null,"unit_price":null,"variants":["free"],"highlights":[]},{"id":"meta-llama/llama-2-70b-chat-hf","author":"meta-llama","name":"Llama 2 70B Chat Hf","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.64,"output_per_m":0.8,"unit":null,"unit_price":null,"highlights":[]},{"id":"meta-llama/llama-3.2-11b-vision-instruct","author":"meta-llama","name":"Llama 3.2 11B Vision Instruct","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":128000,"input_per_m":0.345,"output_per_m":0.345,"unit":null,"unit_price":null,"created":1727222400,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":128000,"description":"Open Llama multimodal model for image understanding and text reasoning","highlights":["Vision"]},{"id":"meta-llama/llama-3.2-1b-instruct","author":"meta-llama","name":"Llama 3.2 1B Instruct","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":16000,"input_per_m":0.005,"output_per_m":0.01,"unit":null,"unit_price":null,"variants":["free"],"created":1735689600,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":4096,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","highlights":["Lowest cost","Tools"]},{"id":"meta-llama/llama-3.2-1b-instruct:free","author":"meta-llama","name":"Llama 3.2 1B Instruct (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":16000,"input_per_m":0,"output_per_m":0,"unit":null,"unit_price":null,"variants":["free"],"created":1735689600,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":4096,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","highlights":["Free","Tools"]},{"id":"meta-llama/llama-3.2-3b-instruct","author":"meta-llama","name":"Llama 3.2 3B Instruct","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":16000,"input_per_m":0.02,"output_per_m":0.02,"unit":null,"unit_price":null,"variants":["free"],"created":1735689600,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":4096,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","highlights":["Lowest cost","Tools"]},{"id":"meta-llama/llama-3.2-3b-instruct:free","author":"meta-llama","name":"Llama 3.2 3B Instruct (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":16000,"input_per_m":0,"output_per_m":0,"unit":null,"unit_price":null,"variants":["free"],"created":1735689600,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":4096,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","highlights":["Free","Tools"]},{"id":"meta-llama/llama-3.2-90b-vision-instruct","author":"meta-llama","name":"Llama 3.2 90B Vision Instruct","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":16000,"input_per_m":0.35,"output_per_m":0.4,"unit":null,"unit_price":null,"created":1727222400,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":4096,"description":"Open Llama multimodal model for image understanding and text reasoning","highlights":["Vision","Tools"]},{"id":"meta-llama/llama-3.3-70b","author":"meta-llama","name":"Llama 3.3 70B","provider":"together","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":128000,"input_per_m":1.04,"output_per_m":1.04,"unit":null,"unit_price":null,"created":1743897600,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":4096,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","highlights":["Tools"]},{"id":"meta-llama/llama-3.3-70b-instruct","author":"meta-llama","name":"Llama-3.3-70B-Instruct","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":128000,"input_per_m":0.23,"output_per_m":0.4,"unit":null,"unit_price":null,"created":1733443200,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":4096,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","highlights":["Tools"]},{"id":"meta-llama/llama-3.3-70b-instruct:free","author":"meta-llama","name":"Llama-3.3-70B-Instruct (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":128000,"input_per_m":0,"output_per_m":0,"unit":null,"unit_price":null,"variants":["free"],"created":1733443200,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":4096,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","highlights":["Free","Tools"]},{"id":"meta-llama/llama-4-maverick-17b-128e-instruct-fp8","author":"meta-llama","name":"Llama-4-Maverick-17B-128E-Instruct-FP8","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":128000,"input_per_m":0.2,"output_per_m":0.8,"unit":null,"unit_price":null,"created":1743811200,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":4096,"description":"Open multimodal Llama model for strong reasoning and fast responses","highlights":["Vision","Tools"]},{"id":"meta-llama/llama-4-maverick-17b-128e-instruct-turbo","author":"meta-llama","name":"Llama 4 Maverick 17B 128e Instruct Turbo","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.5,"output_per_m":0.5,"unit":null,"unit_price":null,"highlights":[]},{"id":"meta-llama/llama-4-scout-17b-16e-instruct","author":"meta-llama","name":"Llama 4 Scout 17B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":327680,"input_per_m":0.1,"output_per_m":0.3,"unit":null,"unit_price":null,"variants":["free"],"created":1743811200,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":false,"vision":true,"audio":false},"max_output":16384,"description":"Open multimodal Llama model for long-context analysis and efficient agents","highlights":["Vision","Tools"]},{"id":"meta-llama/llama-4-scout-17b-16e-instruct:free","author":"meta-llama","name":"Llama 4 Scout 17B (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":327680,"input_per_m":0.1,"output_per_m":0.3,"unit":null,"unit_price":null,"variants":["free"],"created":1743811200,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":false,"vision":true,"audio":false},"max_output":16384,"description":"Open multimodal Llama model for long-context analysis and efficient agents","highlights":["Free","Vision","Tools"]},{"id":"meta-llama/llama-guard-3-8b","author":"meta-llama","name":"Llama-Guard-3-8B (Deep Infra)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.055,"output_per_m":0.055,"unit":null,"unit_price":null,"variants":["free"],"created":1721692800,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":4096,"description":"Llama 3.1-based safety classifier for moderating prompts and model responses","highlights":[]},{"id":"meta-llama/llama-guard-4-12b","author":"meta-llama","name":"Llama Guard 4 12B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":163840,"input_per_m":0.18,"output_per_m":0.18,"unit":null,"unit_price":null,"variants":["free"],"created":1745971200,"variant":"standard","reasoning":false,"input_modalities":["image","text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":16384,"description":"Safety model for policy screening, moderation, and risk-aware routing workflows","highlights":["Vision"]},{"id":"meta-llama/meta-llama-3-70b-instruct","author":"meta-llama","name":"Llama 3 70B Instruct","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":8192,"input_per_m":0.3,"output_per_m":0.4,"unit":null,"unit_price":null,"created":1713398400,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":true,"reasoning":false,"vision":false,"audio":false},"max_output":8000,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","highlights":[]},{"id":"meta-llama/meta-llama-3-8b-instruct","author":"meta-llama","name":"Meta Llama 3 8B Instruct","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.03,"output_per_m":0.04,"unit":null,"unit_price":null,"variants":["free"],"highlights":["Lowest cost"]},{"id":"meta-llama/meta-llama-3-8b-instruct:free","author":"meta-llama","name":"Meta Llama 3 8B Instruct (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":null,"input_per_m":0,"output_per_m":0,"unit":null,"unit_price":null,"variants":["free"],"highlights":["Free"]},{"id":"meta-llama/meta-llama-3.1-405b-instruct","author":"meta-llama","name":"Meta Llama 3.1 405B Instruct","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.8,"output_per_m":0.8,"unit":null,"unit_price":null,"highlights":[]},{"id":"meta-llama/meta-llama-3.1-70b-instruct","author":"meta-llama","name":"Llama-3.1-70B-Instruct","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.4,"output_per_m":0.4,"unit":null,"unit_price":null,"created":1721692800,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":false,"vision":false,"audio":false},"max_output":16384,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","highlights":["Tools"]},{"id":"meta-llama/meta-llama-3.1-70b-instruct-turbo","author":"meta-llama","name":"Meta Llama 3.1 70B Instruct Turbo","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.4,"output_per_m":0.4,"unit":null,"unit_price":null,"highlights":[]},{"id":"meta-llama/meta-llama-3.1-8b-instruct","author":"meta-llama","name":"Llama-3.1-8B-Instruct","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.02,"output_per_m":0.05,"unit":null,"unit_price":null,"variants":["free"],"created":1721692800,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":false,"vision":false,"audio":false},"max_output":117964,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","highlights":["Lowest cost","Tools"]},{"id":"meta-llama/meta-llama-3.1-8b-instruct-turbo","author":"meta-llama","name":"Meta Llama 3.1 8B Instruct Turbo","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":128000,"input_per_m":0.02,"output_per_m":0.04,"unit":null,"unit_price":null,"variants":["free"],"created":1721692800,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":128000,"description":"Compact Llama instruction model for fast chat and local deployment","highlights":["Lowest cost","Tools"]},{"id":"meta-llama/meta-llama-3.1-8b-instruct-turbo:free","author":"meta-llama","name":"Meta Llama 3.1 8B Instruct Turbo (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":128000,"input_per_m":0.02,"output_per_m":0.04,"unit":null,"unit_price":null,"variants":["free"],"created":1721692800,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":128000,"description":"Compact Llama instruction model for fast chat and local deployment","highlights":["Free","Tools"]},{"id":"meta-llama/meta-llama-3.1-8b-instruct:free","author":"meta-llama","name":"Llama-3.1-8B-Instruct (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":131072,"input_per_m":0,"output_per_m":0,"unit":null,"unit_price":null,"variants":["free"],"created":1721692800,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":false,"vision":false,"audio":false},"max_output":117964,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","highlights":["Free","Tools"]},{"id":"meta/muse-glimmer-30b","author":"meta","name":"Muse Glimmer 30B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.3,"output_per_m":1.2,"unit":null,"unit_price":null,"created":1786320000,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":32768,"description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","highlights":["Vision","Reasoning","Tools"]},{"id":"microsoft/phi-3-medium-4k-instruct","author":"microsoft","name":"Phi 3 Medium 4K Instruct","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.14,"output_per_m":0.14,"unit":null,"unit_price":null,"variants":["free"],"highlights":[]},{"id":"microsoft/phi-4","author":"microsoft","name":"Phi 4","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":16384,"input_per_m":0.07,"output_per_m":0.14,"unit":null,"unit_price":null,"variants":["free"],"created":1736467200,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":true,"reasoning":false,"vision":false,"audio":false},"max_output":14745,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","highlights":[]},{"id":"microsoft/phi-4-multimodal-instruct","author":"microsoft","name":"Phi 4 Multimodal","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":128000,"input_per_m":0.05,"output_per_m":0.1,"unit":null,"unit_price":null,"variants":["free"],"created":1753488000,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":16384,"description":"Compact GPT model for low-latency assistance and high-volume workloads","highlights":[]},{"id":"microsoft/phi-4-multimodal-instruct:free","author":"microsoft","name":"Phi 4 Multimodal (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":128000,"input_per_m":0,"output_per_m":0,"unit":null,"unit_price":null,"variants":["free"],"created":1753488000,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":16384,"description":"Compact GPT model for low-latency assistance and high-volume workloads","highlights":["Free"]},{"id":"microsoft/phi-4-reasoning-plus","author":"microsoft","name":"Phi-4-reasoning-plus","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":32000,"input_per_m":0.07,"output_per_m":0.35,"unit":null,"unit_price":null,"created":1733875200,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":4096,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","highlights":["Reasoning"]},{"id":"microsoft/phi-4-reasoning-plus:free","author":"microsoft","name":"Phi-4-reasoning-plus (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":32000,"input_per_m":0,"output_per_m":0,"unit":null,"unit_price":null,"variants":["free"],"created":1733875200,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":4096,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","highlights":["Free","Reasoning"]},{"id":"microsoft/wizardlm-2-7b","author":"microsoft","name":"WizardLM 2 7B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.055,"output_per_m":0.055,"unit":null,"unit_price":null,"variants":["free"],"highlights":[]},{"id":"microsoft/wizardlm-2-7b:free","author":"microsoft","name":"WizardLM 2 7B (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":null,"input_per_m":0,"output_per_m":0,"unit":null,"unit_price":null,"variants":["free"],"highlights":["Free"]},{"id":"minimax/minimax-m2","author":"minimax","name":"MiniMax-M2","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":204800,"input_per_m":0.254,"output_per_m":1.02,"unit":null,"unit_price":null,"created":1761523200,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":131072,"description":"MiniMax model for chat, coding, office work, and agentic tasks","highlights":["Reasoning","Tools"]},{"id":"minimax/minimax-m2.1","author":"minimax","name":"MiniMax-M2.1","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":204800,"input_per_m":0.27,"output_per_m":0.95,"unit":null,"unit_price":null,"created":1766448000,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":131072,"description":"MiniMax model for chat, coding, office work, and agentic tasks","highlights":["Reasoning","Tools"]},{"id":"minimax/minimax-m2.1-highspeed","author":"minimax","name":"MiniMax M2.1 Highspeed","provider":"minimax","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.6,"output_per_m":2.4,"unit":null,"unit_price":null,"highlights":[]},{"id":"minimax/minimax-m2.5","author":"minimax","name":"MiniMax-M2.5","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":204800,"input_per_m":0.15,"output_per_m":1.15,"unit":null,"unit_price":null,"created":1770854400,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":131072,"description":"MiniMax model for chat, coding, office work, and agentic tasks","highlights":["Reasoning","Tools"]},{"id":"minimax/minimax-m2.5-highspeed","author":"minimax","name":"MiniMax-M2.5-highspeed","provider":"minimax","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":204800,"input_per_m":0.54,"output_per_m":2.16,"unit":null,"unit_price":null,"created":1770940800,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":131072,"description":"High-speed MiniMax model for low-latency coding and agent workflows","highlights":["Reasoning","Tools"]},{"id":"minimax/minimax-m2.7","author":"minimax","name":"MiniMax-M2.7","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":204800,"input_per_m":0.25,"output_per_m":1,"unit":null,"unit_price":null,"created":1773792000,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":131072,"description":"MiniMax model for chat, coding, office work, and agentic tasks","highlights":["Reasoning","Tools"]},{"id":"minimax/minimax-m2.7-highspeed","author":"minimax","name":"MiniMax-M2.7-highspeed","provider":"minimax","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":204800,"input_per_m":0.6,"output_per_m":2.4,"unit":null,"unit_price":null,"created":1773792000,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":131072,"description":"High-speed MiniMax model for low-latency coding and agent workflows","highlights":["Reasoning","Tools"]},{"id":"minimax/minimax-m3","author":"minimax","name":"MiniMax-M3","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1048576,"input_per_m":0.28,"output_per_m":1.1,"unit":null,"unit_price":null,"created":1780272000,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":512000,"description":"MiniMax multimodal model for long-context coding, perception, and agent planning","highlights":["Vision","Reasoning","Tools"]},{"id":"mistralai/codestral-2508","author":"mistralai","name":"Codestral 25.08","provider":"mistral","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":256000,"input_per_m":0.3,"output_per_m":0.9,"unit":null,"unit_price":null,"created":1753833600,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":false,"vision":false,"audio":false},"max_output":8192,"description":"Mistral code model for low-latency completion, fill-in-the-middle, and code generation","highlights":["Tools"]},{"id":"mistralai/codestral-embed","author":"mistralai","name":"Codestral Embed","provider":"mistral","status":"live","blocked_by":null,"kind":"embedding","free_kind":null,"context":null,"input_per_m":0.15,"output_per_m":null,"unit":null,"unit_price":null,"highlights":[]},{"id":"mistralai/codestral-latest","author":"mistralai","name":"Codestral (latest)","provider":"mistral","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":256000,"input_per_m":0.3,"output_per_m":0.9,"unit":null,"unit_price":null,"created":1716940800,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":4096,"description":"Mistral code model for completions, refactors, and developer IDE workflows","highlights":["Tools"]},{"id":"mistralai/devstral-2512","author":"mistralai","name":"Devstral 2","provider":"mistral","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.44,"output_per_m":2.2,"unit":null,"unit_price":null,"created":1765238400,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":262144,"description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","highlights":["Tools"]},{"id":"mistralai/devstral-small-2505","author":"mistralai","name":"Devstral Small 2505","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":128000,"input_per_m":0.06,"output_per_m":0.12,"unit":null,"unit_price":null,"variants":["free"],"created":1746576000,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":128000,"description":"Legacy model retained for compatibility with older integrations","highlights":["Tools"]},{"id":"mistralai/devstral-small-2507","author":"mistralai","name":"Devstral Small","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":128000,"input_per_m":0.07,"output_per_m":0.28,"unit":null,"unit_price":null,"variants":["free"],"created":1752105600,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":128000,"description":"Legacy model retained for compatibility with older integrations","highlights":["Tools"]},{"id":"mistralai/ministral-14b-2512","author":"mistralai","name":"Ministral 3 14B","provider":"mistral","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.2,"output_per_m":0.2,"unit":null,"unit_price":null,"created":1764633600,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":false,"vision":true,"audio":false},"max_output":262144,"description":"Open vision-language model for efficient local deployment, instruction following, and tool use","highlights":["Vision","Tools"]},{"id":"mistralai/ministral-14b-latest","author":"mistralai","name":"Ministral 14B","provider":"mistral","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.2,"output_per_m":0.2,"unit":null,"unit_price":null,"created":1764633600,"variant":"standard","reasoning":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":256000,"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","highlights":["Vision"]},{"id":"mistralai/ministral-3b-2512","author":"mistralai","name":"Ministral 3 3B","provider":"mistral","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.1,"output_per_m":0.1,"unit":null,"unit_price":null,"created":1764633600,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":false,"vision":true,"audio":false},"max_output":262144,"description":"Compact open vision-language model for edge deployment, instruction following, and tool use","highlights":["Vision","Tools"]},{"id":"mistralai/ministral-3b-latest","author":"mistralai","name":"Ministral 3B (latest)","provider":"mistral","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.1,"output_per_m":0.1,"unit":null,"unit_price":null,"created":1727740800,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":128000,"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","highlights":["Vision","Tools"]},{"id":"mistralai/ministral-8b-2512","author":"mistralai","name":"Ministral 3 8B","provider":"mistral","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.15,"output_per_m":0.15,"unit":null,"unit_price":null,"created":1764633600,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":false,"vision":true,"audio":false},"max_output":262144,"description":"Compact open vision-language model for edge deployment, instruction following, and tool use","highlights":["Vision","Tools"]},{"id":"mistralai/ministral-8b-latest","author":"mistralai","name":"Ministral 8B (latest)","provider":"mistral","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.15,"output_per_m":0.15,"unit":null,"unit_price":null,"created":1727740800,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":128000,"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","highlights":["Vision","Tools"]},{"id":"mistralai/mistral-7b-instruct-v0.1","author":"mistralai","name":"Mistral 7B Instruct V0.1","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.055,"output_per_m":0.055,"unit":null,"unit_price":null,"variants":["free"],"highlights":[]},{"id":"mistralai/mistral-7b-instruct-v0.2","author":"mistralai","name":"mistral-7b-instruct-v0.2","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":32000,"input_per_m":0.055,"output_per_m":0.055,"unit":null,"unit_price":null,"variants":["free"],"created":1748217600,"variant":"standard","reasoning":false,"input_modalities":["text","pdf"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":8192,"description":"Mistral 7B Instruct is a compact, 7B parameter model optimized for fast and efficient text and code generation with a 32K token context window.","highlights":[]},{"id":"mistralai/mistral-7b-instruct-v0.3","author":"mistralai","name":"mistral-7b-instruct-v0.3","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":127000,"input_per_m":0.028,"output_per_m":0.054,"unit":null,"unit_price":null,"variants":["free"],"created":1748217600,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":false,"vision":false,"audio":false},"max_output":127000,"description":"Mistral-7B-Instruct-v0.3 model is a fine-tuned version of the Mistral 7B base model, optimized for instruction-following tasks. Released in 2023, it is intended for demonstration purposes and does not include built-in guardrails or moderation features.","highlights":["Tools"]},{"id":"mistralai/mistral-7b-instruct-v0.3:free","author":"mistralai","name":"mistral-7b-instruct-v0.3 (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":127000,"input_per_m":0,"output_per_m":0,"unit":null,"unit_price":null,"variants":["free"],"created":1748217600,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":false,"vision":false,"audio":false},"max_output":127000,"description":"Mistral-7B-Instruct-v0.3 model is a fine-tuned version of the Mistral 7B base model, optimized for instruction-following tasks. Released in 2023, it is intended for demonstration purposes and does not include built-in guardrails or moderation features.","highlights":["Free","Tools"]},{"id":"mistralai/mistral-embed","author":"mistralai","name":"Mistral Embed","provider":"mistral","status":"live","blocked_by":null,"kind":"embedding","free_kind":null,"context":8000,"input_per_m":0.1,"output_per_m":null,"unit":null,"unit_price":null,"created":1702252800,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":3072,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","highlights":[]},{"id":"mistralai/mistral-medium","author":"mistralai","name":"Mistral Medium (latest)","provider":"mistral","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":1.5,"output_per_m":7.5,"unit":null,"unit_price":null,"created":1777420800,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":262144,"description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","highlights":["Vision","Reasoning","Tools"]},{"id":"mistralai/mistral-medium-2505","author":"mistralai","name":"Mistral Medium 3","provider":"mistral","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.4,"output_per_m":2,"unit":null,"unit_price":null,"created":1746576000,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":131072,"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","highlights":["Vision","Tools"]},{"id":"mistralai/mistral-medium-2508","author":"mistralai","name":"Mistral Medium 3.1","provider":"mistral","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.4,"output_per_m":2,"unit":null,"unit_price":null,"created":1754956800,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":262144,"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","highlights":["Vision","Tools"]},{"id":"mistralai/mistral-medium-2604","author":"mistralai","name":"Mistral Medium 3.5","provider":"mistral","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":1.5,"output_per_m":7.5,"unit":null,"unit_price":null,"created":1777420800,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":262144,"description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","highlights":["Vision","Reasoning","Tools"]},{"id":"mistralai/mistral-medium-3","author":"mistralai","name":"Mistral Medium 3","provider":"mistral","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.4,"output_per_m":2,"unit":null,"unit_price":null,"created":1746576000,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":32768,"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","highlights":["Vision"]},{"id":"mistralai/mistral-medium-3-5","author":"mistralai","name":"Mistral Medium 3.5","provider":"mistral","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":256000,"input_per_m":1.5,"output_per_m":7.5,"unit":null,"unit_price":null,"created":1777420800,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":32768,"description":"Mistral Medium 3.5 is a 128B dense open-weights flagship model for instruction-following, reasoning, coding, long-horizon agentic work, tool use, structured output, and multimodal prompts. It supports a 256k context window and configurable reasoning effort.","highlights":["Vision","Reasoning","Tools"]},{"id":"mistralai/mistral-medium-3.5","author":"mistralai","name":"Mistral Medium 3.5","provider":"mistral","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":256000,"input_per_m":1.5,"output_per_m":7.5,"unit":null,"unit_price":null,"created":1777420800,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":32768,"description":"Mistral Medium 3.5 is a 128B dense open-weights flagship model for instruction-following, reasoning, coding, long-horizon agentic work, tool use, structured output, and multimodal prompts. It supports a 256k context window and configurable reasoning effort.","highlights":["Vision","Reasoning","Tools"]},{"id":"mistralai/mistral-medium-latest","author":"mistralai","name":"Mistral Medium (latest)","provider":"mistral","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":1.5,"output_per_m":7.5,"unit":null,"unit_price":null,"created":1777420800,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":262144,"description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","highlights":["Vision","Reasoning","Tools"]},{"id":"mistralai/mistral-nemo-instruct-2407","author":"mistralai","name":"Mistral Nemo","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":128000,"input_per_m":0.029,"output_per_m":0.03,"unit":null,"unit_price":null,"variants":["free"],"created":1719792000,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":128000,"description":"Efficient Mistral-NVIDIA open model for multilingual chat and local deployment","highlights":["Lowest cost","Tools"]},{"id":"mistralai/mistral-nemo-instruct-2407:free","author":"mistralai","name":"Mistral Nemo (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":128000,"input_per_m":0.029,"output_per_m":0.03,"unit":null,"unit_price":null,"variants":["free"],"created":1719792000,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":128000,"description":"Efficient Mistral-NVIDIA open model for multilingual chat and local deployment","highlights":["Free","Tools"]},{"id":"mistralai/mistral-small-24b-instruct-2501","author":"mistralai","name":"Mistral Small 3","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":32768,"input_per_m":0.05,"output_per_m":0.08,"unit":null,"unit_price":null,"variants":["free"],"created":1738195200,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":true,"reasoning":false,"vision":false,"audio":false},"max_output":16384,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","highlights":[]},{"id":"mistralai/mistral-small-24b-instruct-2501:free","author":"mistralai","name":"Mistral Small 3 (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":32768,"input_per_m":0.05,"output_per_m":0.08,"unit":null,"unit_price":null,"variants":["free"],"created":1738195200,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":true,"reasoning":false,"vision":false,"audio":false},"max_output":16384,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","highlights":["Free"]},{"id":"mistralai/mistral-small-2603","author":"mistralai","name":"Mistral Small 4","provider":"mistral","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.15,"output_per_m":0.6,"unit":null,"unit_price":null,"created":1773619200,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":256000,"description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","highlights":["Vision","Reasoning","Tools"]},{"id":"mistralai/mistral-small-3.1-24b-instruct-2503","author":"mistralai","name":"Mistral Small 3.1 24B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.05,"output_per_m":0.1,"unit":null,"unit_price":null,"variants":["free"],"created":1742169600,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":false,"vision":true,"audio":false},"max_output":16384,"description":"Efficient multimodal model for instruction following, coding, reasoning, and function calling","highlights":["Vision","Tools"]},{"id":"mistralai/mistral-small-3.1-24b-instruct-2503:free","author":"mistralai","name":"Mistral Small 3.1 24B (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":131072,"input_per_m":0,"output_per_m":0,"unit":null,"unit_price":null,"variants":["free"],"created":1742169600,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":false,"vision":true,"audio":false},"max_output":16384,"description":"Efficient multimodal model for instruction following, coding, reasoning, and function calling","highlights":["Free","Vision","Tools"]},{"id":"mistralai/mistral-small-3.2-24b-instruct-2506","author":"mistralai","name":"Mistral-Small-3.2-24B-Instruct-2506","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.075,"output_per_m":0.2,"unit":null,"unit_price":null,"variants":["free"],"created":1752624000,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":false,"vision":true,"audio":false},"max_output":131072,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","highlights":["Vision","Tools"]},{"id":"mistralai/mistral-small-latest","author":"mistralai","name":"Mistral Small (latest)","provider":"mistral","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.15,"output_per_m":0.6,"unit":null,"unit_price":null,"created":1773619200,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":256000,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","highlights":["Vision","Reasoning","Tools"]},{"id":"mistralai/mixtral-8x7b-instruct-v0.1","author":"mistralai","name":"Mixtral 8x7B Instruct v0.1","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":32000,"input_per_m":0.54,"output_per_m":0.54,"unit":null,"unit_price":null,"created":1702252800,"variant":"thinking","reasoning":true,"input_modalities":["text","pdf"],"output_modalities":["text"],"capabilities":{"tools":false,"json":true,"reasoning":true,"vision":false,"audio":false},"max_output":4096,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","highlights":["Reasoning"]},{"id":"mistralai/voxtral-small-2507","author":"mistralai","name":"Voxtral Small","provider":"mistral","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":32768,"input_per_m":0.1,"output_per_m":0.4,"unit":null,"unit_price":null,"created":1752537600,"variant":"standard","reasoning":false,"input_modalities":["text","audio"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":true},"max_output":32000,"description":"Instruct model with native audio input for speech understanding and tool use","highlights":["Tools"]},{"id":"mistralai/voxtral-small-latest","author":"mistralai","name":"Voxtral Small (latest)","provider":"mistral","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":32768,"input_per_m":0.1,"output_per_m":0.4,"unit":null,"unit_price":null,"created":1752537600,"variant":"standard","reasoning":false,"input_modalities":["text","audio"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":true},"max_output":32000,"description":"Instruct model with native audio input for speech understanding and tool use","highlights":["Tools"]},{"id":"moonshotai/kimi-k2-instruct","author":"moonshotai","name":"Kimi K2 Instruct","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":256000,"input_per_m":0.5,"output_per_m":2,"unit":null,"unit_price":null,"created":1752192000,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":false,"vision":false,"audio":false},"max_output":8192,"description":"Non-thinking Kimi K2 MoE instruction model for coding and tool-using agents","highlights":["Tools"]},{"id":"moonshotai/kimi-k2-instruct-0905","author":"moonshotai","name":"Kimi K2 Instruct","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":32768,"input_per_m":0.4,"output_per_m":2,"unit":null,"unit_price":null,"created":1725494400,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":4096,"description":"Kimi model for long-context chat, coding, and agentic reasoning","highlights":["Tools"]},{"id":"moonshotai/kimi-k2-thinking","author":"moonshotai","name":"Kimi K2 Thinking","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.47,"output_per_m":2,"unit":null,"unit_price":null,"created":1757030400,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":262144,"description":"Legacy model retained for compatibility with older integrations","highlights":["Reasoning","Tools"]},{"id":"moonshotai/kimi-k2.5","author":"moonshotai","name":"Kimi K2.5 Thinking","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.45,"output_per_m":2.25,"unit":null,"unit_price":null,"created":1767225600,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":65536,"description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","highlights":["Vision","Reasoning","Tools"]},{"id":"moonshotai/kimi-k2.5-turbo","author":"moonshotai","name":"Kimi K2.5 Turbo","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.6,"output_per_m":3,"unit":null,"unit_price":null,"highlights":[]},{"id":"moonshotai/kimi-k2.6","author":"moonshotai","name":"Kimi K2.6","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.75,"output_per_m":3.5,"unit":null,"unit_price":null,"created":1776729600,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":262144,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","highlights":["Vision","Reasoning","Tools"]},{"id":"moonshotai/kimi-k2.7-code","author":"moonshotai","name":"Kimi K2.7 Code","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.68,"output_per_m":3.4,"unit":null,"unit_price":null,"created":1781222400,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":262144,"description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","highlights":["Vision","Reasoning","Tools"]},{"id":"moonshotai/kimi-k2.7-code-highspeed","author":"moonshotai","name":"Kimi K2.7 Code HighSpeed","provider":"moonshot","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":1.9,"output_per_m":8,"unit":null,"unit_price":null,"created":1781222400,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":262144,"description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","highlights":["Vision","Reasoning","Tools"]},{"id":"moonshotai/kimi-k3","author":"moonshotai","name":"Kimi K3","provider":"moonshot","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1048576,"input_per_m":0.304,"output_per_m":11.936,"unit":null,"unit_price":null,"created":1784160000,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":131072,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","highlights":["Vision","Reasoning","Tools"]},{"id":"nousresearch/hermes-3-llama-3.1-405b","author":"nousresearch","name":"Hermes 3 405B Instruct","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":1,"output_per_m":1,"unit":null,"unit_price":null,"created":1723766400,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":true,"reasoning":false,"vision":false,"audio":false},"max_output":16384,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","highlights":[]},{"id":"nousresearch/hermes-3-llama-3.1-70b","author":"nousresearch","name":"Hermes 3 70B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":65536,"input_per_m":0.7,"output_per_m":0.7,"unit":null,"unit_price":null,"created":1723939200,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":8192,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","highlights":["Tools"]},{"id":"novasky-ai/sky-t1-32b-preview","author":"novasky-ai","name":"Sky T1 32B Preview","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.12,"output_per_m":0.18,"unit":null,"unit_price":null,"variants":["free"],"highlights":[]},{"id":"novita/deepseek/deepseek-ocr-2","author":"novita","name":"DeepSeek OCR 2","provider":"novita","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":8192,"input_per_m":0.03,"output_per_m":0.03,"unit":null,"unit_price":null,"created":1769472000,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":8192,"description":"High-accuracy OCR model for extracting text from documents, screenshots, receipts, and natural scenes","highlights":["Lowest cost","Vision"]},{"id":"novita/deepseek/deepseek-r1/community","author":"novita","name":"Community","provider":"novita","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":4,"output_per_m":4,"unit":null,"unit_price":null,"highlights":[]},{"id":"novita/deepseek/deepseek-v4-flash-0731-p","author":"novita","name":"DeepSeek V4 Flash 0731 P","provider":"novita","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.44,"output_per_m":1.32,"unit":null,"unit_price":null,"highlights":[]},{"id":"novita/deepseek/deepseek-v4-pro-0813-p","author":"novita","name":"DeepSeek V4 Pro 0813 P","provider":"novita","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":1.32,"output_per_m":3.96,"unit":null,"unit_price":null,"highlights":[]},{"id":"novita/deepseek/deepseek-v4.1-flash","author":"novita","name":"DeepSeek V4.1 Flash","provider":"novita","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":0.3,"output_per_m":1.2,"unit":null,"unit_price":null,"created":1788998400,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":384000,"description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","highlights":["Vision","Reasoning","Tools"]},{"id":"novita/deepseek/deepseek-v4.1-flash-dst","author":"novita","name":"DeepSeek V4.1 Flash Dst","provider":"novita","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.3,"output_per_m":1.2,"unit":null,"unit_price":null,"highlights":[]},{"id":"novita/deepseek/deepseek-v4.1-flash-p","author":"novita","name":"DeepSeek V4.1 Flash P","provider":"novita","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.3,"output_per_m":1.2,"unit":null,"unit_price":null,"highlights":[]},{"id":"novita/deepseek/deepseek_v3","author":"novita","name":"DeepSeek V3","provider":"novita","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":164000,"input_per_m":0.89,"output_per_m":0.89,"unit":null,"unit_price":null,"created":1735171200,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":false,"vision":false,"audio":false},"max_output":164000,"description":"DeepSeek chat model for instruction following, coding, and analysis","highlights":["Tools"]},{"id":"novita/inclusionai/ling-3.0-flash-fin","author":"novita","name":"Ling 3.0 Flash Fin","provider":"novita","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.075,"output_per_m":0.22,"unit":null,"unit_price":null,"created":1787788800,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":32768,"description":"Finance-enhanced model for financial research, multi-step investment workflows, and long-horizon planning and execution","highlights":["Reasoning","Tools"]},{"id":"novita/inclusionai/ling-3.0-flash-sante","author":"novita","name":"Ling 3.0 Flash Sante","provider":"novita","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.075,"output_per_m":0.22,"unit":null,"unit_price":null,"created":1788480000,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":32768,"description":"Health and medicine specialization of Ling 3.0 Flash for medical reasoning and evidence-based retrieval","highlights":["Reasoning","Tools"]},{"id":"novita/inclusionai/ling-3.0-flash-vl","author":"novita","name":"Ling 3.0 Flash VL","provider":"novita","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.075,"output_per_m":0.22,"unit":null,"unit_price":null,"created":1788998400,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":32768,"description":"Native multimodal hybrid MoE model for image and video understanding, reasoning, and visual agents","highlights":["Vision","Reasoning","Tools"]},{"id":"novita/inclusionai/ling-3.1-flash","author":"novita","name":"Ling 3.1 Flash","provider":"novita","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.3,"output_per_m":0.9,"unit":null,"unit_price":null,"created":1790640000,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":false,"audio":false},"max_output":32768,"description":"Efficient model for low-latency assistance, extraction, and routine automation","highlights":["Reasoning","Tools"]},{"id":"novita/meta-llama/llama-3.1-8b-instruct","author":"novita","name":"Llama-3.1-8B-Instruct","provider":"novita","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.02,"output_per_m":0.05,"unit":null,"unit_price":null,"created":1721692800,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":false,"vision":false,"audio":false},"max_output":117964,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","highlights":["Tools"]},{"id":"novita/microsoft/wizardlm-2-8x22b","author":"novita","name":"WizardLM 2 8x22B (Deep Infra)","provider":"novita","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":65536,"input_per_m":0.62,"output_per_m":0.62,"unit":null,"unit_price":null,"created":1713139200,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":8000,"description":"Microsoft WizardLM instruction-tuned Mixtral MoE for multilingual dialogue and complex tasks","highlights":[]},{"id":"novita/mindai/macaron-v1-tall","author":"novita","name":"Macaron V1 Tall","provider":"novita","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.2475,"output_per_m":1.43,"unit":null,"unit_price":null,"created":1784592000,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":32768,"description":"Qwen3.6-based Mixture-of-LoRA model with specialists for chat, personal agents, coding, and generative UI","highlights":["Reasoning","Tools"]},{"id":"novita/mindai/macaron-v1-venti","author":"novita","name":"Macaron V1 Venti","provider":"novita","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1048576,"input_per_m":0.825,"output_per_m":2.475,"unit":null,"unit_price":null,"created":1784592000,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":131072,"description":"GLM-5.2-based Mixture-of-LoRA model with specialists for chat, personal agents, coding, and generative UI","highlights":["Reasoning","Tools"]},{"id":"novita/minimaxai/minimax-m1-80k","author":"novita","name":"MiniMax M1 80K","provider":"novita","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":0.55,"output_per_m":2.2,"unit":null,"unit_price":null,"created":1750118400,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":false,"audio":false},"max_output":40000,"description":"Open hybrid-attention MoE reasoning model with a million-token context and an 80K thinking budget","highlights":["Reasoning","Tools"]},{"id":"novita/moonshotai/kimi-k2-0905","author":"novita","name":"Kimi K2 (09/05)","provider":"novita","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.6,"output_per_m":2.5,"unit":null,"unit_price":null,"created":1757030400,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":16384,"description":"Kimi model for long-context chat, coding, and agentic reasoning","highlights":["Tools"]},{"id":"novita/moonshotai/kimi-k3-p","author":"novita","name":"Kimi K3 P","provider":"novita","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":3,"output_per_m":15,"unit":null,"unit_price":null,"highlights":[]},{"id":"novita/qwen/qwen3-omni-30b-a3b-thinking","author":"novita","name":"Qwen3 Omni 30B A3B Thinking","provider":"novita","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":65536,"input_per_m":0.25,"output_per_m":0.97,"unit":null,"unit_price":null,"created":1758499200,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":true},"max_output":16384,"description":"Multimodal reasoning model accepting text, images, video, and audio with text output","highlights":["Vision","Reasoning","Tools"]},{"id":"novita/qwen/qwen3.8-flash","author":"novita","name":"Qwen3.8 Flash","provider":"novita","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":0.15,"output_per_m":0.47,"unit":null,"unit_price":null,"created":1787702400,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":131072,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","highlights":["Vision","Reasoning","Tools"]},{"id":"novita/qwen/qwen3.8-max","author":"novita","name":"Qwen3.8 Max","provider":"novita","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":2,"output_per_m":6,"unit":null,"unit_price":null,"created":1785715200,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":131072,"description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","highlights":["Vision","Reasoning","Tools"]},{"id":"novita/sao10k/l3-8b-stheno-v3.2","author":"novita","name":"Sao10K Stheno 8b","provider":"novita","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":16384,"input_per_m":0.05,"output_per_m":0.05,"unit":null,"unit_price":null,"created":1704067200,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":8192,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","highlights":[]},{"id":"novita/stepfun/step-5-preview","author":"novita","name":"Step 5 Preview","provider":"novita","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":1,"output_per_m":2.7,"unit":null,"unit_price":null,"created":1789516800,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":65536,"description":"StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window","highlights":["Vision","Reasoning","Tools"]},{"id":"novita/tencent/hy4-preview","author":"novita","name":"Hy4 preview","provider":"novita","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1024000,"input_per_m":0.834,"output_per_m":2.501,"unit":null,"unit_price":null,"created":1787875200,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":64000,"description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","highlights":["Reasoning","Tools"]},{"id":"novita/xiaomimimo/mimo-v2.6-flash","author":"novita","name":"MiMo-V2.6-Flash","provider":"novita","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1048576,"input_per_m":0.14,"output_per_m":0.28,"unit":null,"unit_price":null,"created":1790035200,"variant":"thinking","reasoning":true,"input_modalities":["text","image","audio","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":true},"max_output":131072,"description":"MiMo Flash model for multimodal coding agents and long-context automation","highlights":["Vision","Reasoning","Tools"]},{"id":"novita/xiaomimimo/mimo-v2.6-pro","author":"novita","name":"MiMo-V2.6-Pro","provider":"novita","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1048576,"input_per_m":0.435,"output_per_m":0.87,"unit":null,"unit_price":null,"created":1790035200,"variant":"thinking","reasoning":true,"input_modalities":["text","image","audio","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":true},"max_output":131072,"description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","highlights":["Vision","Reasoning","Tools"]},{"id":"novita/zai-org/autoglm-phone-9b-multilingual","author":"novita","name":"AutoGLM Phone 9B Multilingual","provider":"novita","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":65536,"input_per_m":0.035,"output_per_m":0.138,"unit":null,"unit_price":null,"created":1765324800,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":65536,"description":"Multilingual visual model for operating smartphone interfaces and mobile agents","highlights":["Vision"]},{"id":"novita/zai-org/glm-4.5v","author":"novita","name":"GLM-4.5V","provider":"novita","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":64000,"input_per_m":0.6,"output_per_m":1.8,"unit":null,"unit_price":null,"created":1754870400,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":16384,"description":"GLM vision model for visual reasoning, documents, and multimodal agents","highlights":["Vision","Reasoning","Tools"]},{"id":"novita/zai-org/glm-5.3-p","author":"novita","name":"GLM 5.3 P","provider":"novita","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":1.4,"output_per_m":4.4,"unit":null,"unit_price":null,"highlights":[]},{"id":"nvidia/llama-3.1-nemotron-70b-instruct","author":"nvidia","name":"Llama 3.1 Nemotron 70B Instruct","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":128000,"input_per_m":1.2,"output_per_m":1.2,"unit":null,"unit_price":null,"created":1744675200,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":8192,"description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","highlights":["Tools"]},{"id":"nvidia/llama-3.3-nemotron-super-49b-v1.5","author":"nvidia","name":"Llama 3.3 Nemotron Super 49B v1.5","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.4,"output_per_m":0.4,"unit":null,"unit_price":null,"created":1753401600,"variant":"standard","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":65536,"description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","highlights":["Reasoning","Tools"]},{"id":"nvidia/llama-nemotron-embed-vl-1b-v2","author":"nvidia","name":"llama-nemotron-embed-vl-1b-v2","provider":"deepinfra","status":"live","blocked_by":null,"kind":"embedding","free_kind":null,"context":32768,"input_per_m":0.01,"output_per_m":null,"unit":null,"unit_price":null,"created":1770681600,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":2048,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","highlights":["Vision"]},{"id":"nvidia/nemotron-3-embed-1b-bf16","author":"nvidia","name":"Nemotron 3 Embed 1B Bf16","provider":"deepinfra","status":"live","blocked_by":null,"kind":"embedding","free_kind":null,"context":null,"input_per_m":0.015,"output_per_m":null,"unit":null,"unit_price":null,"highlights":[]},{"id":"nvidia/nemotron-3-embed-1b-nvfp4","author":"nvidia","name":"Nemotron 3 Embed 1B Nvfp4","provider":"deepinfra","status":"live","blocked_by":null,"kind":"embedding","free_kind":null,"context":null,"input_per_m":0.01,"output_per_m":null,"unit":null,"unit_price":null,"highlights":[]},{"id":"nvidia/nemotron-3-embed-8b","author":"nvidia","name":"Nemotron 3 Embed 8B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"embedding","free_kind":null,"context":null,"input_per_m":0.035,"output_per_m":null,"unit":null,"unit_price":null,"highlights":[]},{"id":"nvidia/nemotron-3-nano-30b-a3b","author":"nvidia","name":"Nemotron 3 Nano 30B A3B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.05,"output_per_m":0.2,"unit":null,"unit_price":null,"variants":["free"],"created":1765756800,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":262144,"description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","highlights":["Reasoning","Tools"]},{"id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning","author":"nvidia","name":"Nemotron 3 Nano Omni 30B A3B Reasoning","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.2,"output_per_m":0.8,"unit":null,"unit_price":null,"created":1777334400,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":true},"max_output":65536,"description":"Open Nemotron omni model combining reasoning with text, vision, and audio","highlights":["Vision","Reasoning","Tools"]},{"id":"nvidia/nemotron-3-ultra-550b-a55b","author":"nvidia","name":"Nemotron 3 Ultra 550B A55B","provider":"together","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":202800,"input_per_m":0.6,"output_per_m":3.6,"unit":null,"unit_price":null,"created":1780531200,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":false,"audio":false},"max_output":182520,"description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...","highlights":["Reasoning","Tools"]},{"id":"nvidia/nemotron-4-340b-instruct","author":"nvidia","name":"Nemotron 4 340B Instruct","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":4.2,"output_per_m":4.2,"unit":null,"unit_price":null,"highlights":[]},{"id":"nvidia/nemotron-content-safety-3.5","author":"nvidia","name":"Nemotron Content Safety 3.5","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.2,"output_per_m":0.2,"unit":null,"unit_price":null,"variants":["free"],"highlights":[]},{"id":"nvidia/nvidia-nemotron-3-super-120b-a12b","author":"nvidia","name":"nvidia-nemotron-3-super-120b-a12b","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.085,"output_per_m":0.4,"unit":null,"unit_price":null,"created":1773187200,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":false,"audio":false},"max_output":262144,"description":"NVIDIA Nemotron 3 Super is a hybrid Mixture-of-Experts (MoE) model engineered for highest compute efficiency and accuracy in multi-agent applications and specialized agentic systems. It is optimized to run many collaborating agents per application on a single ","highlights":["Reasoning","Tools"]},{"id":"nvidia/nvidia-nemotron-3-super-120b-a12b:free","author":"nvidia","name":"nvidia-nemotron-3-super-120b-a12b (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":262144,"input_per_m":0.085,"output_per_m":0.4,"unit":null,"unit_price":null,"variants":["free"],"created":1773187200,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":false,"audio":false},"max_output":262144,"description":"NVIDIA Nemotron 3 Super is a hybrid Mixture-of-Experts (MoE) model engineered for highest compute efficiency and accuracy in multi-agent applications and specialized agentic systems. It is optimized to run many collaborating agents per application on a single ","highlights":["Free","Reasoning","Tools"]},{"id":"nvidia/nvidia-nemotron-3-ultra-550b-a55b","author":"nvidia","name":"Nemotron 3 Ultra","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.5,"output_per_m":2.2,"unit":null,"unit_price":null,"created":1780531200,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":false,"audio":false},"max_output":262144,"description":"Nemotron 3 Ultra is a powerful MoE model designed for long-running agents across coding, deep research, and enterprise automation.","highlights":["Reasoning","Tools"]},{"id":"nvidia/nvidia-nemotron-3-ultra-550b-a55b-bf16","author":"nvidia","name":"Nemotron 3 Ultra 550B A55B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":1,"output_per_m":5,"unit":null,"unit_price":null,"created":1780531200,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":65000,"description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","highlights":["Reasoning","Tools"]},{"id":"nvidia/nvidia-nemotron-3.5-lightning","author":"nvidia","name":"Nvidia Nemotron 3.5 Lightning","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.06,"output_per_m":0.16,"unit":null,"unit_price":null,"variants":["free"],"highlights":[]},{"id":"nvidia/nvidia-nemotron-nano-12b-v2-vl","author":"nvidia","name":"Nvidia Nemotron Nano 12B V2 VL","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.2,"output_per_m":0.6,"unit":null,"unit_price":null,"highlights":[]},{"id":"nvidia/nvidia-nemotron-nano-9b-v2","author":"nvidia","name":"nvidia-nemotron-nano-9b-v2","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.04,"output_per_m":0.16,"unit":null,"unit_price":null,"variants":["free"],"created":1755475200,"variant":"standard","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":131072,"description":"Compact Nemotron model for efficient reasoning and deployable AI agents","highlights":["Reasoning","Tools"]},{"id":"openai/gpt-3.5-turbo","author":"openai","name":"GPT-3.5 Turbo","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":16385,"input_per_m":0.5,"output_per_m":1.5,"unit":null,"unit_price":null,"created":1677628800,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":4096,"description":"Compact GPT model for low-latency assistance and high-volume workloads","highlights":[]},{"id":"openai/gpt-3.5-turbo-0125","author":"openai","name":"GPT-3.5 Turbo 0125","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":16384,"input_per_m":0.5,"output_per_m":1.5,"unit":null,"unit_price":null,"created":1706140800,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":4096,"description":"Compact GPT model for low-latency assistance and high-volume workloads","highlights":[]},{"id":"openai/gpt-3.5-turbo-16k","author":"openai","name":"GPT-3.5 Turbo 16k","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":16385,"input_per_m":3,"output_per_m":4,"unit":null,"unit_price":null,"created":1693180800,"variant":"standard","reasoning":false,"input_modalities":["text","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":false,"vision":false,"audio":false},"max_output":4096,"description":"Compact GPT model for low-latency assistance and high-volume workloads","highlights":["Tools"]},{"id":"openai/gpt-4","author":"openai","name":"GPT-4","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":8192,"input_per_m":30,"output_per_m":60,"unit":null,"unit_price":null,"created":1699228800,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":8192,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","highlights":["Tools"]},{"id":"openai/gpt-4-0613","author":"openai","name":"GPT 4 0613","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":30,"output_per_m":60,"unit":null,"unit_price":null,"highlights":[]},{"id":"openai/gpt-4-turbo","author":"openai","name":"GPT-4 Turbo","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":128000,"input_per_m":10,"output_per_m":30,"unit":null,"unit_price":null,"created":1699228800,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":4096,"description":"Compact GPT model for low-latency assistance and high-volume workloads","highlights":["Vision"]},{"id":"openai/gpt-4-turbo-2024-04-09","author":"openai","name":"GPT-4 Turbo","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":128000,"input_per_m":10,"output_per_m":30,"unit":null,"unit_price":null,"created":1699228800,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":4096,"description":"Compact GPT model for low-latency assistance and high-volume workloads","highlights":["Vision"]},{"id":"openai/gpt-4.1","author":"openai","name":"GPT 4.1","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1047576,"input_per_m":2,"output_per_m":8,"unit":null,"unit_price":null,"created":1744588800,"variant":"standard","reasoning":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":false,"vision":true,"audio":false},"max_output":32768,"description":"Long-lived GPT workhorse for coding, instruction following, and production apps","highlights":["Vision","Tools"]},{"id":"openai/gpt-4.1-2025-04-14","author":"openai","name":"GPT 4.1","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1047576,"input_per_m":2,"output_per_m":8,"unit":null,"unit_price":null,"created":1744588800,"variant":"standard","reasoning":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":false,"vision":true,"audio":false},"max_output":32768,"description":"Long-lived GPT workhorse for coding, instruction following, and production apps","highlights":["Vision","Tools"]},{"id":"openai/gpt-4.1-mini","author":"openai","name":"GPT 4.1 Mini","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1047576,"input_per_m":0.4,"output_per_m":1.6,"unit":null,"unit_price":null,"created":1744588800,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":32768,"description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","highlights":["Vision"]},{"id":"openai/gpt-4.1-mini-2025-04-14","author":"openai","name":"GPT 4.1 Mini","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1047576,"input_per_m":0.4,"output_per_m":1.6,"unit":null,"unit_price":null,"created":1744588800,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":32768,"description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","highlights":["Vision"]},{"id":"openai/gpt-4.1-nano","author":"openai","name":"GPT 4.1 Nano","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1047576,"input_per_m":0.1,"output_per_m":0.4,"unit":null,"unit_price":null,"created":1744588800,"variant":"standard","reasoning":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":32768,"description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","highlights":["Vision"]},{"id":"openai/gpt-4.1-nano-2025-04-14","author":"openai","name":"GPT 4.1 Nano","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1047576,"input_per_m":0.1,"output_per_m":0.4,"unit":null,"unit_price":null,"created":1744588800,"variant":"standard","reasoning":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":32768,"description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","highlights":["Vision"]},{"id":"openai/gpt-4o","author":"openai","name":"GPT-4o","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":128000,"input_per_m":2.5,"output_per_m":10,"unit":null,"unit_price":null,"created":1715558400,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":16384,"description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","highlights":["Vision","Tools"]},{"id":"openai/gpt-4o-2024-05-13","author":"openai","name":"GPT-4o","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":128000,"input_per_m":5,"output_per_m":15,"unit":null,"unit_price":null,"created":1715558400,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":16384,"description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","highlights":["Vision","Tools"]},{"id":"openai/gpt-4o-2024-08-06","author":"openai","name":"GPT-4o","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":128000,"input_per_m":2.5,"output_per_m":10,"unit":null,"unit_price":null,"created":1715558400,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":16384,"description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","highlights":["Vision","Tools"]},{"id":"openai/gpt-4o-2024-11-20","author":"openai","name":"GPT-4o","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":128000,"input_per_m":2.5,"output_per_m":10,"unit":null,"unit_price":null,"created":1715558400,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":16384,"description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","highlights":["Vision","Tools"]},{"id":"openai/gpt-4o-mini","author":"openai","name":"GPT-4o mini","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":128000,"input_per_m":0.15,"output_per_m":0.6,"unit":null,"unit_price":null,"created":1721260800,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":16384,"description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","highlights":["Vision"]},{"id":"openai/gpt-4o-mini-2024-07-18","author":"openai","name":"GPT-4o mini","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":128000,"input_per_m":0.15,"output_per_m":0.6,"unit":null,"unit_price":null,"created":1721260800,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":16384,"description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","highlights":["Vision"]},{"id":"openai/gpt-5","author":"openai","name":"GPT 5","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":400000,"input_per_m":1.25,"output_per_m":10,"unit":null,"unit_price":null,"created":1754524800,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","highlights":["Vision","Reasoning","Tools"]},{"id":"openai/gpt-5-2025-08-07","author":"openai","name":"GPT 5","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":400000,"input_per_m":1.25,"output_per_m":10,"unit":null,"unit_price":null,"created":1754524800,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","highlights":["Vision","Reasoning","Tools"]},{"id":"openai/gpt-5-mini","author":"openai","name":"GPT 5 Mini","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":400000,"input_per_m":0.25,"output_per_m":2,"unit":null,"unit_price":null,"created":1754524800,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"Small GPT-5 for responsive agents, coding help, and everyday automation","highlights":["Vision","Reasoning"]},{"id":"openai/gpt-5-mini-2025-08-07","author":"openai","name":"GPT 5 Mini","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":400000,"input_per_m":0.25,"output_per_m":2,"unit":null,"unit_price":null,"created":1754524800,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"Small GPT-5 for responsive agents, coding help, and everyday automation","highlights":["Vision","Reasoning"]},{"id":"openai/gpt-5-nano","author":"openai","name":"GPT 5 Nano","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":400000,"input_per_m":0.05,"output_per_m":0.4,"unit":null,"unit_price":null,"created":1754524800,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","highlights":["Vision","Reasoning"]},{"id":"openai/gpt-5-nano-2025-08-07","author":"openai","name":"GPT 5 Nano","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":400000,"input_per_m":0.05,"output_per_m":0.4,"unit":null,"unit_price":null,"created":1754524800,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","highlights":["Vision","Reasoning"]},{"id":"openai/gpt-5.1","author":"openai","name":"GPT 5.1","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":400000,"input_per_m":1.25,"output_per_m":10,"unit":null,"unit_price":null,"created":1762992000,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","highlights":["Vision","Reasoning","Tools"]},{"id":"openai/gpt-5.1-2025-11-13","author":"openai","name":"GPT 5.1","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":400000,"input_per_m":1.25,"output_per_m":10,"unit":null,"unit_price":null,"created":1762992000,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","highlights":["Vision","Reasoning","Tools"]},{"id":"openai/gpt-5.2","author":"openai","name":"GPT 5.2","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":400000,"input_per_m":1.75,"output_per_m":14,"unit":null,"unit_price":null,"created":1765411200,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","highlights":["Vision","Reasoning","Tools"]},{"id":"openai/gpt-5.2-2025-12-11","author":"openai","name":"GPT 5.2","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":400000,"input_per_m":1.75,"output_per_m":14,"unit":null,"unit_price":null,"created":1765411200,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","highlights":["Vision","Reasoning","Tools"]},{"id":"openai/gpt-5.4","author":"openai","name":"GPT 5.4","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1050000,"input_per_m":2.5,"output_per_m":15,"unit":null,"unit_price":null,"created":1772668800,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","highlights":["Longest context","Vision","Reasoning","Tools"]},{"id":"openai/gpt-5.4-2026-03-05","author":"openai","name":"GPT 5.4","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1050000,"input_per_m":2.5,"output_per_m":15,"unit":null,"unit_price":null,"created":1772668800,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","highlights":["Longest context","Vision","Reasoning","Tools"]},{"id":"openai/gpt-5.4-mini","author":"openai","name":"GPT 5.4 Mini","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":400000,"input_per_m":0.75,"output_per_m":4.5,"unit":null,"unit_price":null,"created":1773705600,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","highlights":["Vision","Reasoning","Tools"]},{"id":"openai/gpt-5.4-mini-2026-03-17","author":"openai","name":"GPT 5.4 Mini","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":400000,"input_per_m":0.75,"output_per_m":4.5,"unit":null,"unit_price":null,"created":1773705600,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","highlights":["Vision","Reasoning","Tools"]},{"id":"openai/gpt-5.4-nano","author":"openai","name":"GPT 5.4 Nano","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":400000,"input_per_m":0.2,"output_per_m":1.25,"unit":null,"unit_price":null,"created":1773705600,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","highlights":["Vision","Reasoning","Tools"]},{"id":"openai/gpt-5.4-nano-2026-03-17","author":"openai","name":"GPT 5.4 Nano","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":400000,"input_per_m":0.2,"output_per_m":1.25,"unit":null,"unit_price":null,"created":1773705600,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","highlights":["Vision","Reasoning","Tools"]},{"id":"openai/gpt-5.5","author":"openai","name":"GPT 5.5","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1050000,"input_per_m":5,"output_per_m":30,"unit":null,"unit_price":null,"created":1776902400,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"Default frontier GPT for coding, computer use, research, and knowledge work","highlights":["Longest context","Vision","Reasoning","Tools"]},{"id":"openai/gpt-5.5-2026-04-23","author":"openai","name":"GPT 5.5","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1050000,"input_per_m":5,"output_per_m":30,"unit":null,"unit_price":null,"created":1776902400,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"Default frontier GPT for coding, computer use, research, and knowledge work","highlights":["Longest context","Vision","Reasoning","Tools"]},{"id":"openai/gpt-5.6-luna","author":"openai","name":"GPT 5.6 Luna","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1050000,"input_per_m":0.2,"output_per_m":1.2,"unit":null,"unit_price":null,"created":1783555200,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","highlights":["Longest context","Vision","Reasoning","Tools"]},{"id":"openai/gpt-5.6-sol","author":"openai","name":"GPT 5.6 Sol","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1050000,"input_per_m":4,"output_per_m":20,"unit":null,"unit_price":null,"created":1783555200,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","highlights":["Longest context","Vision","Reasoning","Tools"]},{"id":"openai/gpt-5.6-terra","author":"openai","name":"GPT 5.6 Terra","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1050000,"input_per_m":2,"output_per_m":12,"unit":null,"unit_price":null,"created":1783555200,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","highlights":["Vision","Reasoning","Tools"]},{"id":"openai/gpt-6-astra","author":"openai","name":"GPT 6 Astra","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1050000,"input_per_m":10,"output_per_m":50,"unit":null,"unit_price":null,"created":1788480000,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","highlights":["Vision","Reasoning","Tools"]},{"id":"openai/gpt-6-luna","author":"openai","name":"GPT 6 Luna","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1050000,"input_per_m":0.1,"output_per_m":0.5,"unit":null,"unit_price":null,"created":1790035200,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"OpenAI's most efficient model for focused, high-volume tasks","highlights":["Vision","Reasoning","Tools"]},{"id":"openai/gpt-6-sol","author":"openai","name":"GPT 6 Sol","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1050000,"input_per_m":2,"output_per_m":10,"unit":null,"unit_price":null,"created":1790035200,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"OpenAI model for complex coding and agentic workflows","highlights":["Vision","Reasoning","Tools"]},{"id":"openai/gpt-6.1-sol","author":"openai","name":"GPT 6.1 Sol","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1050000,"input_per_m":2,"output_per_m":10,"unit":null,"unit_price":null,"created":1790640000,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":128000,"description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","highlights":["Vision","Reasoning","Tools"]},{"id":"openai/gpt-oss-120b","author":"openai","name":"GPT OSS 120B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":128000,"input_per_m":0.037,"output_per_m":0.17,"unit":null,"unit_price":null,"variants":["free"],"created":1754352000,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":false,"audio":false},"max_output":16384,"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","highlights":["Reasoning","Tools"]},{"id":"openai/gpt-oss-120b-turbo","author":"openai","name":"GPT OSS 120B Turbo","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.15,"output_per_m":0.6,"unit":null,"unit_price":null,"highlights":[]},{"id":"openai/gpt-oss-20b","author":"openai","name":"GPT OSS 20B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.03,"output_per_m":0.14,"unit":null,"unit_price":null,"variants":["free"],"created":1754352000,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":16384,"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","highlights":["Reasoning","Tools"]},{"id":"openai/gpt-oss-20b:free","author":"openai","name":"GPT OSS 20B (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":131072,"input_per_m":0.03,"output_per_m":0.14,"unit":null,"unit_price":null,"variants":["free"],"created":1754352000,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":16384,"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","highlights":["Free","Reasoning","Tools"]},{"id":"openai/gpt-oss-safeguard-20b","author":"openai","name":"GPT OSS Safeguard 20B","provider":"groq","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":128000,"input_per_m":0.075,"output_per_m":0.3,"unit":null,"unit_price":null,"variants":["free"],"created":1761696000,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":16384,"description":"Safety model for policy screening, moderation, and risk-aware routing workflows","highlights":["Reasoning"]},{"id":"openai/o1","author":"openai","name":"o1","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":200000,"input_per_m":15,"output_per_m":60,"unit":null,"unit_price":null,"created":1734480000,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":100000,"description":"O-series reasoning model for hard analysis, math, coding, and planning","highlights":["Vision","Reasoning","Tools"]},{"id":"openai/o1-2024-12-17","author":"openai","name":"o1","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":200000,"input_per_m":15,"output_per_m":60,"unit":null,"unit_price":null,"created":1734480000,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":100000,"description":"O-series reasoning model for hard analysis, math, coding, and planning","highlights":["Vision","Reasoning","Tools"]},{"id":"openai/o3","author":"openai","name":"o3","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":200000,"input_per_m":2,"output_per_m":8,"unit":null,"unit_price":null,"created":1744761600,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":100000,"description":"O-series reasoning model for hard analysis, math, coding, and planning","highlights":["Vision","Reasoning","Tools"]},{"id":"openai/o3-2025-04-16","author":"openai","name":"o3","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":200000,"input_per_m":2,"output_per_m":8,"unit":null,"unit_price":null,"created":1744761600,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":100000,"description":"O-series reasoning model for hard analysis, math, coding, and planning","highlights":["Vision","Reasoning","Tools"]},{"id":"openai/o3-mini","author":"openai","name":"o3-mini","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":200000,"input_per_m":1.1,"output_per_m":4.4,"unit":null,"unit_price":null,"created":1738281600,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":100000,"description":"O-series reasoning model for hard analysis, math, coding, and planning","highlights":["Vision","Reasoning","Tools"]},{"id":"openai/o3-mini-2025-01-31","author":"openai","name":"o3-mini","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":200000,"input_per_m":1.1,"output_per_m":4.4,"unit":null,"unit_price":null,"created":1738281600,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":100000,"description":"O-series reasoning model for hard analysis, math, coding, and planning","highlights":["Vision","Reasoning","Tools"]},{"id":"openai/o4-mini","author":"openai","name":"o4-mini","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":200000,"input_per_m":1.1,"output_per_m":4.4,"unit":null,"unit_price":null,"created":1744761600,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":100000,"description":"O-series reasoning model for hard analysis, math, coding, and planning","highlights":["Vision","Reasoning","Tools"]},{"id":"openai/o4-mini-2025-04-16","author":"openai","name":"o4-mini","provider":"openai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":200000,"input_per_m":1.1,"output_per_m":4.4,"unit":null,"unit_price":null,"created":1744761600,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":100000,"description":"O-series reasoning model for hard analysis, math, coding, and planning","highlights":["Vision","Reasoning","Tools"]},{"id":"openai/text-embedding-3-large","author":"openai","name":"text-embedding-3-large","provider":"openai","status":"live","blocked_by":null,"kind":"embedding","free_kind":null,"context":8191,"input_per_m":0.13,"output_per_m":null,"unit":null,"unit_price":null,"created":1706140800,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":3072,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","highlights":[]},{"id":"openai/text-embedding-3-small","author":"openai","name":"text-embedding-3-small","provider":"openai","status":"live","blocked_by":null,"kind":"embedding","free_kind":null,"context":8192,"input_per_m":0.02,"output_per_m":null,"unit":null,"unit_price":null,"created":1706140800,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":1536,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","highlights":[]},{"id":"openai/text-embedding-ada-002","author":"openai","name":"text-embedding-ada-002","provider":"openai","status":"live","blocked_by":null,"kind":"embedding","free_kind":null,"context":8192,"input_per_m":0.1,"output_per_m":null,"unit":null,"unit_price":null,"created":1671062400,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":1536,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","highlights":[]},{"id":"openbmb/minicpm-llama3-v-2_5","author":"openbmb","name":"Minicpm Llama3 V 2.5","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.34,"output_per_m":0.34,"unit":null,"unit_price":null,"highlights":[]},{"id":"openchat/openchat-3.6-8b","author":"openchat","name":"OpenChat 3.6 8B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.055,"output_per_m":0.055,"unit":null,"unit_price":null,"variants":["free"],"highlights":[]},{"id":"openchat/openchat-3.6-8b:free","author":"openchat","name":"OpenChat 3.6 8B (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":null,"input_per_m":0,"output_per_m":0,"unit":null,"unit_price":null,"variants":["free"],"highlights":["Free"]},{"id":"openchat/openchat_3.5","author":"openchat","name":"OpenChat 3.5","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.055,"output_per_m":0.055,"unit":null,"unit_price":null,"variants":["free"],"highlights":[]},{"id":"paddlepaddle/paddleocr-vl-0.9b","author":"paddlepaddle","name":"Paddleocr VL 0.9B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.14,"output_per_m":0.8,"unit":null,"unit_price":null,"highlights":[]},{"id":"pearl-ai/gemma-4-31b-it","author":"pearl-ai","name":"Gemma 4 31B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.2,"output_per_m":0.4,"unit":null,"unit_price":null,"created":1775088000,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":131072,"description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","highlights":["Vision","Reasoning","Tools"]},{"id":"phind/phind-codellama-34b-v2","author":"phind","name":"Phind Codellama 34B V2","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.6,"output_per_m":0.6,"unit":null,"unit_price":null,"highlights":[]},{"id":"qwen/qvq-72b-preview","author":"qwen","name":"Qvq 72B Preview","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.25,"output_per_m":0.5,"unit":null,"unit_price":null,"highlights":[]},{"id":"qwen/qwen-coder-plus","author":"qwen","name":"Qwen Coder Plus","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.8,"output_per_m":4,"unit":null,"unit_price":null,"highlights":[]},{"id":"qwen/qwen-flash","author":"qwen","name":"Qwen Flash","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":0.25,"output_per_m":2,"unit":null,"unit_price":null,"created":1753660800,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":32768,"description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","highlights":["Reasoning","Tools"]},{"id":"qwen/qwen-max","author":"qwen","name":"Qwen Max","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":32768,"input_per_m":1.6,"output_per_m":6.4,"unit":null,"unit_price":null,"created":1712102400,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":8192,"description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","highlights":["Tools"]},{"id":"qwen/qwen-mt-flash","author":"qwen","name":"Qwen Mt Flash","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.16,"output_per_m":0.49,"unit":null,"unit_price":null,"highlights":[]},{"id":"qwen/qwen-mt-lite","author":"qwen","name":"Qwen Mt Lite","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.12,"output_per_m":0.36,"unit":null,"unit_price":null,"highlights":[]},{"id":"qwen/qwen-mt-plus","author":"qwen","name":"Qwen-MT Plus","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":16384,"input_per_m":2.46,"output_per_m":7.37,"unit":null,"unit_price":null,"created":1735689600,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":8192,"description":"Translation model for multilingual conversion, localization, and cross-language workflows","highlights":[]},{"id":"qwen/qwen-mt-turbo","author":"qwen","name":"Qwen-MT Turbo","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":16384,"input_per_m":0.16,"output_per_m":0.49,"unit":null,"unit_price":null,"created":1735689600,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":8192,"description":"Translation model for multilingual conversion, localization, and cross-language workflows","highlights":[]},{"id":"qwen/qwen-plus-2025-04-28","author":"qwen","name":"Qwen Plus","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":0.26,"output_per_m":0.78,"unit":null,"unit_price":null,"created":1706140800,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":32768,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","highlights":["Reasoning","Tools"]},{"id":"qwen/qwen-plus-2025-07-14","author":"qwen","name":"Qwen Plus","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":0.26,"output_per_m":0.78,"unit":null,"unit_price":null,"created":1706140800,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":32768,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","highlights":["Reasoning","Tools"]},{"id":"qwen/qwen-plus-2025-09-11","author":"qwen","name":"Qwen Plus","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":0.26,"output_per_m":0.78,"unit":null,"unit_price":null,"created":1706140800,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":32768,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","highlights":["Reasoning","Tools"]},{"id":"qwen/qwen-plus-2025-12-01","author":"qwen","name":"Qwen Plus","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":0.26,"output_per_m":0.78,"unit":null,"unit_price":null,"created":1706140800,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":32768,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","highlights":["Reasoning","Tools"]},{"id":"qwen/qwen-plus-latest","author":"qwen","name":"Qwen Plus","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":0.26,"output_per_m":0.78,"unit":null,"unit_price":null,"created":1706140800,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":32768,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","highlights":["Reasoning","Tools"]},{"id":"qwen/qwen-vl-max","author":"qwen","name":"Qwen-VL Max","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.8,"output_per_m":3.2,"unit":null,"unit_price":null,"created":1712534400,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":8192,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","highlights":["Vision","Tools"]},{"id":"qwen/qwen-vl-ocr","author":"qwen","name":"Qwen-VL OCR","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":34096,"input_per_m":0.07,"output_per_m":0.16,"unit":null,"unit_price":null,"created":1730073600,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":4096,"description":"OCR model for extracting structured text from documents and screenshots","highlights":["Vision"]},{"id":"qwen/qwen-vl-plus","author":"qwen","name":"Qwen-VL Plus","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.21,"output_per_m":0.63,"unit":null,"unit_price":null,"created":1706140800,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":8192,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","highlights":["Vision","Tools"]},{"id":"qwen/qwen2-72b-instruct","author":"qwen","name":"Qwen2 72B Instruct","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.35,"output_per_m":0.4,"unit":null,"unit_price":null,"highlights":[]},{"id":"qwen/qwen2-7b-instruct","author":"qwen","name":"Qwen2 7B Instruct","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.055,"output_per_m":0.055,"unit":null,"unit_price":null,"variants":["free"],"highlights":[]},{"id":"qwen/qwen2-7b-instruct:free","author":"qwen","name":"Qwen2 7B Instruct (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":null,"input_per_m":0,"output_per_m":0,"unit":null,"unit_price":null,"variants":["free"],"highlights":["Free"]},{"id":"qwen/qwen2.5-72b-instruct","author":"qwen","name":"Qwen2.5 72B Instruct","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.36,"output_per_m":0.4,"unit":null,"unit_price":null,"created":1725148800,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":8192,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","highlights":["Tools"]},{"id":"qwen/qwen2.5-7b-instruct","author":"qwen","name":"Qwen2.5 7B Instruct","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.04,"output_per_m":0.1,"unit":null,"unit_price":null,"variants":["free"],"created":1725148800,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":8192,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","highlights":["Tools"]},{"id":"qwen/qwen2.5-7b-instruct:free","author":"qwen","name":"Qwen2.5 7B Instruct (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":131072,"input_per_m":0,"output_per_m":0,"unit":null,"unit_price":null,"variants":["free"],"created":1725148800,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":8192,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","highlights":["Free","Tools"]},{"id":"qwen/qwen2.5-coder-32b-instruct","author":"qwen","name":"Qwen2.5-Coder-32B-Instruct","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.06,"output_per_m":0.15,"unit":null,"unit_price":null,"variants":["free"],"created":1731369600,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":false,"vision":false,"audio":false},"max_output":8192,"description":"Qwen coding model for software agents, repository edits, and code reasoning","highlights":["Tools"]},{"id":"qwen/qwen2.5-coder-7b","author":"qwen","name":"Qwen2.5 Coder 7B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.025,"output_per_m":0.05,"unit":null,"unit_price":null,"variants":["free"],"highlights":[]},{"id":"qwen/qwen2.5-coder-7b:free","author":"qwen","name":"Qwen2.5 Coder 7B (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":null,"input_per_m":0,"output_per_m":0,"unit":null,"unit_price":null,"variants":["free"],"highlights":["Free"]},{"id":"qwen/qwen2.5-vl-32b-instruct","author":"qwen","name":"Qwen 2.5 VL 32B Instruct","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":32000,"input_per_m":0.2,"output_per_m":0.6,"unit":null,"unit_price":null,"created":1730419200,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":4096,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","highlights":["Vision","Tools"]},{"id":"qwen/qwen3-14b","author":"qwen","name":"Qwen3 14B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.12,"output_per_m":0.24,"unit":null,"unit_price":null,"variants":["free"],"created":1743465600,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":8192,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","highlights":["Reasoning","Tools"]},{"id":"qwen/qwen3-14b:free","author":"qwen","name":"Qwen3 14B (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":131072,"input_per_m":0.12,"output_per_m":0.24,"unit":null,"unit_price":null,"variants":["free"],"created":1743465600,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":8192,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","highlights":["Free","Reasoning","Tools"]},{"id":"qwen/qwen3-235b-a22b","author":"qwen","name":"Qwen3 235B-A22B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.18,"output_per_m":0.54,"unit":null,"unit_price":null,"created":1743465600,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":16384,"description":"Large open Qwen MoE for multilingual reasoning, coding, and tool use","highlights":["Reasoning","Tools"]},{"id":"qwen/qwen3-235b-a22b-instruct-2507","author":"qwen","name":"Qwen3 235B-A22B Instruct 2507","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.09,"output_per_m":0.55,"unit":null,"unit_price":null,"created":1753056000,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":false,"vision":false,"audio":false},"max_output":16384,"description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","highlights":["Tools"]},{"id":"qwen/qwen3-235b-a22b-thinking-2507","author":"qwen","name":"Qwen 3 235B Thinking","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.23,"output_per_m":2.3,"unit":null,"unit_price":null,"created":1751328000,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":4096,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","highlights":["Reasoning","Tools"]},{"id":"qwen/qwen3-30b-a3b","author":"qwen","name":"Qwen3 30B A3B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":41000,"input_per_m":0.12,"output_per_m":0.5,"unit":null,"unit_price":null,"created":1748736000,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":41000,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","highlights":["Vision","Tools"]},{"id":"qwen/qwen3-30b-a3b-instruct-2507","author":"qwen","name":"Qwen3 30B A3B Instruct 2507","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262000,"input_per_m":0.13,"output_per_m":0.52,"unit":null,"unit_price":null,"created":1753833600,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":false,"vision":false,"audio":false},"max_output":262000,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","highlights":["Tools"]},{"id":"qwen/qwen3-30b-a3b-thinking-2507","author":"qwen","name":"Qwen3 30B A3B Thinking 2507","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.2,"output_per_m":2.4,"unit":null,"unit_price":null,"created":1753920000,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":false,"audio":false},"max_output":131072,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","highlights":["Reasoning","Tools"]},{"id":"qwen/qwen3-30b-a3b:free","author":"qwen","name":"Qwen3 30B A3B (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":41000,"input_per_m":0.12,"output_per_m":0.5,"unit":null,"unit_price":null,"variants":["free"],"created":1748736000,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":41000,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","highlights":["Free","Vision","Tools"]},{"id":"qwen/qwen3-32b","author":"qwen","name":"Qwen3 32B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.08,"output_per_m":0.28,"unit":null,"unit_price":null,"variants":["free"],"created":1743465600,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":16384,"description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","highlights":["Reasoning","Tools"]},{"id":"qwen/qwen3-32b:free","author":"qwen","name":"Qwen3 32B (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":131072,"input_per_m":0.08,"output_per_m":0.28,"unit":null,"unit_price":null,"variants":["free"],"created":1743465600,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":16384,"description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","highlights":["Free","Reasoning","Tools"]},{"id":"qwen/qwen3-8b","author":"qwen","name":"Qwen3 8B","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.18,"output_per_m":0.7,"unit":null,"unit_price":null,"created":1743465600,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":8192,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","highlights":["Reasoning","Tools"]},{"id":"qwen/qwen3-coder-30b-a3b-instruct","author":"qwen","name":"Qwen3-Coder 30B-A3B Instruct","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.07,"output_per_m":0.26,"unit":null,"unit_price":null,"variants":["free"],"created":1743465600,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":65536,"description":"Smaller Qwen coder for efficient local agents and repo-level fixes","highlights":["Tools"]},{"id":"qwen/qwen3-coder-480b-a35b-instruct","author":"qwen","name":"Qwen3-Coder 480B-A35B Instruct","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.3,"output_per_m":1,"unit":null,"unit_price":null,"created":1743465600,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":65536,"description":"Open Qwen coding heavyweight for repository reasoning and agentic engineering","highlights":["Tools"]},{"id":"qwen/qwen3-coder-480b-a35b-instruct-turbo","author":"qwen","name":"Qwen3 Coder 480B A35B Instruct Turbo","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.3,"output_per_m":1,"unit":null,"unit_price":null,"created":1753228800,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":false,"vision":false,"audio":false},"max_output":66536,"description":"Qwen coding model for software agents, repository edits, and code reasoning","highlights":["Tools"]},{"id":"qwen/qwen3-coder-flash","author":"qwen","name":"Qwen3 Coder Flash","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":0.195,"output_per_m":0.975,"unit":null,"unit_price":null,"created":1753660800,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":65536,"description":"Qwen coding model for software agents, repository edits, and code reasoning","highlights":["Tools"]},{"id":"qwen/qwen3-coder-next","author":"qwen","name":"Qwen3 Coder Next","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.3,"output_per_m":1.5,"unit":null,"unit_price":null,"created":1760486400,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":false,"audio":false},"max_output":65536,"description":"Qwen coding model for software agents, repository edits, and code reasoning","highlights":["Reasoning","Tools"]},{"id":"qwen/qwen3-coder-plus","author":"qwen","name":"Qwen3 Coder Plus","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1048576,"input_per_m":0.65,"output_per_m":3.25,"unit":null,"unit_price":null,"created":1753228800,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":65536,"description":"Hosted Qwen coder for software agents, repo edits, and long-context code","highlights":["Tools"]},{"id":"qwen/qwen3-coder-plus-2025-07-22","author":"qwen","name":"Qwen3 Coder Plus","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1048576,"input_per_m":0.65,"output_per_m":3.25,"unit":null,"unit_price":null,"created":1753228800,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":65536,"description":"Hosted Qwen coder for software agents, repo edits, and long-context code","highlights":["Tools"]},{"id":"qwen/qwen3-coder-plus-2025-09-23","author":"qwen","name":"Qwen3 Coder Plus","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1048576,"input_per_m":0.65,"output_per_m":3.25,"unit":null,"unit_price":null,"created":1753228800,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":65536,"description":"Hosted Qwen coder for software agents, repo edits, and long-context code","highlights":["Tools"]},{"id":"qwen/qwen3-embedding-0.6b","author":"qwen","name":"Qwen3 Embedding 0.6B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"embedding","free_kind":null,"context":32768,"input_per_m":0.01,"output_per_m":null,"unit":null,"unit_price":null,"created":1748908800,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":1024,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","highlights":[]},{"id":"qwen/qwen3-embedding-0.6b-batch","author":"qwen","name":"Qwen3 Embedding 0.6B Batch","provider":"deepinfra","status":"live","blocked_by":null,"kind":"embedding","free_kind":null,"context":null,"input_per_m":0.005,"output_per_m":null,"unit":null,"unit_price":null,"highlights":[]},{"id":"qwen/qwen3-embedding-4b","author":"qwen","name":"Qwen 3 Embedding 4B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"embedding","free_kind":null,"context":32000,"input_per_m":0.02,"output_per_m":null,"unit":null,"unit_price":null,"created":1735689600,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":2048,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","highlights":[]},{"id":"qwen/qwen3-embedding-4b-batch","author":"qwen","name":"Qwen3 Embedding 4B Batch","provider":"deepinfra","status":"live","blocked_by":null,"kind":"embedding","free_kind":null,"context":null,"input_per_m":0.01,"output_per_m":null,"unit":null,"unit_price":null,"highlights":[]},{"id":"qwen/qwen3-embedding-8b","author":"qwen","name":"Qwen 3 Embedding 8B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"embedding","free_kind":null,"context":32000,"input_per_m":0.01,"output_per_m":null,"unit":null,"unit_price":null,"created":1735689600,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":4096,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","highlights":[]},{"id":"qwen/qwen3-embedding-8b-batch","author":"qwen","name":"Qwen3 Embedding 8B Batch","provider":"deepinfra","status":"live","blocked_by":null,"kind":"embedding","free_kind":null,"context":null,"input_per_m":0.04,"output_per_m":null,"unit":null,"unit_price":null,"highlights":[]},{"id":"qwen/qwen3-max","author":"qwen","name":"Qwen3 Max","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.78,"output_per_m":3.9,"unit":null,"unit_price":null,"created":1758585600,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":65536,"description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","highlights":["Tools"]},{"id":"qwen/qwen3-max-2025-09-23","author":"qwen","name":"Qwen3 Max","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.78,"output_per_m":3.9,"unit":null,"unit_price":null,"created":1758585600,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":65536,"description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","highlights":["Tools"]},{"id":"qwen/qwen3-max-2026-01-23","author":"qwen","name":"Qwen3 Max","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.78,"output_per_m":3.9,"unit":null,"unit_price":null,"created":1758585600,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":65536,"description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","highlights":["Tools"]},{"id":"qwen/qwen3-max-preview","author":"qwen","name":"Qwen3 Max","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.78,"output_per_m":3.9,"unit":null,"unit_price":null,"created":1758585600,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":65536,"description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","highlights":["Tools"]},{"id":"qwen/qwen3-next-80b-a3b-instruct","author":"qwen","name":"Qwen3-Next 80B-A3B Instruct","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.09,"output_per_m":1.1,"unit":null,"unit_price":null,"created":1756684800,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":32768,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","highlights":["Tools"]},{"id":"qwen/qwen3-next-80b-a3b-thinking","author":"qwen","name":"Qwen3-Next 80B-A3B (Thinking)","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.15,"output_per_m":1.2,"unit":null,"unit_price":null,"created":1756684800,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":32768,"description":"Efficient Qwen thinking model for local reasoning, math, and coding agents","highlights":["Reasoning","Tools"]},{"id":"qwen/qwen3-omni-flash","author":"qwen","name":"Qwen3-Omni Flash","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":65536,"input_per_m":0.4,"output_per_m":3,"unit":null,"unit_price":null,"created":1757894400,"variant":"thinking","reasoning":true,"input_modalities":["text","image","audio","video"],"output_modalities":["text","audio"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":true},"max_output":16384,"description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","highlights":["Vision","Reasoning","Tools"]},{"id":"qwen/qwen3-reranker-0.6b","author":"qwen","name":"Qwen3 Reranker 0.6B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"rerank","free_kind":null,"context":40960,"input_per_m":0.01,"output_per_m":null,"unit":null,"unit_price":null,"created":1748908800,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":1024,"description":"Reranking model for improving retrieval quality in search and recommendation systems","highlights":[]},{"id":"qwen/qwen3-reranker-4b","author":"qwen","name":"Qwen3 Reranker 4B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"rerank","free_kind":null,"context":32000,"input_per_m":0.025,"output_per_m":null,"unit":null,"unit_price":null,"created":1753833600,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":4096,"description":"Reranking model for improving retrieval quality in search and recommendation systems","highlights":[]},{"id":"qwen/qwen3-reranker-8b","author":"qwen","name":"Qwen3 Reranker 8B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"rerank","free_kind":null,"context":32768,"input_per_m":0.05,"output_per_m":null,"unit":null,"unit_price":null,"created":1749081600,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":0,"description":"Multilingual query-document reranking model supporting more than 100 languages","highlights":[]},{"id":"qwen/qwen3-vl-235b-a22b-instruct","author":"qwen","name":"Qwen3 VL 235B A22B Instruct","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.2,"output_per_m":0.88,"unit":null,"unit_price":null,"created":1758585600,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":false,"vision":true,"audio":false},"max_output":32768,"description":"Qwen vision-language instruct model for visual reasoning, documents, and agent tasks","highlights":["Vision","Tools"]},{"id":"qwen/qwen3-vl-235b-a22b-thinking","author":"qwen","name":"Qwen3-VL 235B-A22B","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.4,"output_per_m":4,"unit":null,"unit_price":null,"created":1743465600,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":32768,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","highlights":["Vision","Reasoning","Tools"]},{"id":"qwen/qwen3-vl-30b-a3b-instruct","author":"qwen","name":"Qwen3 VL 30B A3B Instruct","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.15,"output_per_m":0.6,"unit":null,"unit_price":null,"created":1759536000,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":false,"vision":true,"audio":false},"max_output":32768,"description":"Open vision-language MoE model for image and video understanding, documents, and visual agents","highlights":["Vision","Tools"]},{"id":"qwen/qwen3-vl-30b-a3b-thinking","author":"qwen","name":"Qwen3-VL 30B-A3B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.29,"output_per_m":0.99,"unit":null,"unit_price":null,"created":1743465600,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":32768,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","highlights":["Vision","Reasoning","Tools"]},{"id":"qwen/qwen3-vl-4b-instruct","author":"qwen","name":"Qwen3 VL 4B Instruct","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.1,"output_per_m":0.6,"unit":null,"unit_price":null,"highlights":[]},{"id":"qwen/qwen3-vl-4b-thinking","author":"qwen","name":"Qwen3 VL 4B Thinking","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.1,"output_per_m":1,"unit":null,"unit_price":null,"highlights":[]},{"id":"qwen/qwen3-vl-8b-instruct","author":"qwen","name":"Qwen3 VL 8B Instruct","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262000,"input_per_m":0.18,"output_per_m":0.69,"unit":null,"unit_price":null,"created":1760486400,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":false,"vision":true,"audio":false},"max_output":262000,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","highlights":["Vision","Tools"]},{"id":"qwen/qwen3-vl-8b-thinking","author":"qwen","name":"Qwen3 VL 8B Thinking","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.18,"output_per_m":2.09,"unit":null,"unit_price":null,"highlights":[]},{"id":"qwen/qwen3-vl-flash","author":"qwen","name":"Qwen3-VL Flash","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.12,"output_per_m":0.96,"unit":null,"unit_price":null,"created":1760486400,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":false,"vision":true,"audio":false},"max_output":65536,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","highlights":["Vision","Tools"]},{"id":"qwen/qwen3-vl-plus","author":"qwen","name":"Qwen3-VL Plus","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.6,"output_per_m":4.8,"unit":null,"unit_price":null,"created":1758585600,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":32768,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","highlights":["Fastest","Vision","Reasoning","Tools"]},{"id":"qwen/qwen3.5-0.8b","author":"qwen","name":"Qwen3.5 0.8B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":32768,"input_per_m":0.01,"output_per_m":0.05,"unit":null,"unit_price":null,"variants":["free"],"created":1761955200,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":8192,"description":"Qwen instruction model for multilingual chat and tool use","highlights":["Lowest cost","Tools"]},{"id":"qwen/qwen3.5-0.8b:free","author":"qwen","name":"Qwen3.5 0.8B (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":32768,"input_per_m":0,"output_per_m":0,"unit":null,"unit_price":null,"variants":["free"],"created":1761955200,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":8192,"description":"Qwen instruction model for multilingual chat and tool use","highlights":["Free","Tools"]},{"id":"qwen/qwen3.5-122b-a10b","author":"qwen","name":"Qwen3.5 122B-A10B","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.26,"output_per_m":2.08,"unit":null,"unit_price":null,"created":1771804800,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":true},"max_output":65536,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","highlights":["Vision","Reasoning","Tools"]},{"id":"qwen/qwen3.5-27b","author":"qwen","name":"Qwen3.5 27B","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.195,"output_per_m":1.56,"unit":null,"unit_price":null,"created":1771804800,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":true},"max_output":65536,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","highlights":["Vision","Reasoning","Tools"]},{"id":"qwen/qwen3.5-2b","author":"qwen","name":"qwen3.5-2b","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.02,"output_per_m":0.1,"unit":null,"unit_price":null,"variants":["free"],"created":1773100800,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":262144,"description":"Qwen3.5-2B is a compact yet capable model from Alibaba's Qwen3.5 series. It features a 262K token context window, support for 201 languages, thinking/reasoning mode, and tool calling for agentic workflows. A strong choice for prototyping, fine-tuning, and effi","highlights":["Vision","Reasoning","Tools"]},{"id":"qwen/qwen3.5-2b:free","author":"qwen","name":"qwen3.5-2b (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":262144,"input_per_m":0,"output_per_m":0,"unit":null,"unit_price":null,"variants":["free"],"created":1773100800,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":262144,"description":"Qwen3.5-2B is a compact yet capable model from Alibaba's Qwen3.5 series. It features a 262K token context window, support for 201 languages, thinking/reasoning mode, and tool calling for agentic workflows. A strong choice for prototyping, fine-tuning, and effi","highlights":["Free","Vision","Reasoning","Tools"]},{"id":"qwen/qwen3.5-35b-a3b","author":"qwen","name":"Qwen3.5 35B-A3B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.14,"output_per_m":1,"unit":null,"unit_price":null,"created":1771804800,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":true},"max_output":65536,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","highlights":["Vision","Reasoning","Tools"]},{"id":"qwen/qwen3.5-397b-a17b","author":"qwen","name":"Qwen3.5 397B-A17B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.45,"output_per_m":3,"unit":null,"unit_price":null,"created":1771113600,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":true},"max_output":65536,"description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","highlights":["Vision","Reasoning","Tools"]},{"id":"qwen/qwen3.5-4b","author":"qwen","name":"Qwen3.5 4B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.03,"output_per_m":0.15,"unit":null,"unit_price":null,"variants":["free"],"created":1772409600,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":32768,"description":"Qwen3.5 4B is a low-cost multimodal reasoning model with 256K context, image and video input, function tools, and structured output.","highlights":["Vision","Reasoning","Tools"]},{"id":"qwen/qwen3.5-9b","author":"qwen","name":"Qwen3.5 9B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.1,"output_per_m":0.15,"unit":null,"unit_price":null,"variants":["free"],"created":1773360000,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":true},"max_output":262144,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","highlights":["Vision","Reasoning","Tools"]},{"id":"qwen/qwen3.5-flash","author":"qwen","name":"Qwen3.5 Flash","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":0.065,"output_per_m":0.26,"unit":null,"unit_price":null,"created":1771804800,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":65536,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","highlights":["Vision","Reasoning","Tools"]},{"id":"qwen/qwen3.5-flash-2026-02-23","author":"qwen","name":"Qwen3.5 Flash","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":0.065,"output_per_m":0.26,"unit":null,"unit_price":null,"created":1771804800,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":65536,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","highlights":["Vision","Reasoning","Tools"]},{"id":"qwen/qwen3.5-omni-flash","author":"qwen","name":"Qwen3.5 Omni Flash","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.4,"output_per_m":3,"unit":null,"unit_price":null,"highlights":[]},{"id":"qwen/qwen3.5-omni-plus","author":"qwen","name":"Qwen3.5 Omni Plus","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":1.4,"output_per_m":11,"unit":null,"unit_price":null,"highlights":[]},{"id":"qwen/qwen3.5-plus","author":"qwen","name":"Qwen3.5 Plus","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":0.3,"output_per_m":1.8,"unit":null,"unit_price":null,"created":1771200000,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":65536,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","highlights":["Vision","Reasoning","Tools"]},{"id":"qwen/qwen3.5-plus-2026-02-15","author":"qwen","name":"Qwen3.5 Plus","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":0.26,"output_per_m":1.56,"unit":null,"unit_price":null,"created":1771200000,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":65536,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","highlights":["Vision","Reasoning","Tools"]},{"id":"qwen/qwen3.5-plus-2026-04-20","author":"qwen","name":"Qwen3.5 Plus","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":0.3,"output_per_m":1.8,"unit":null,"unit_price":null,"created":1771200000,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":65536,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","highlights":["Vision","Reasoning","Tools"]},{"id":"qwen/qwen3.6-27b","author":"qwen","name":"Qwen3.6 27B","provider":"groq","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.32,"output_per_m":3.2,"unit":null,"unit_price":null,"created":1776816000,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":true},"max_output":65536,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","highlights":["Vision","Reasoning","Tools"]},{"id":"qwen/qwen3.6-35b-a3b","author":"qwen","name":"Qwen3.6 35B-A3B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.1,"output_per_m":0.95,"unit":null,"unit_price":null,"created":1776384000,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":true},"max_output":65536,"description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","highlights":["Vision","Reasoning","Tools"]},{"id":"qwen/qwen3.6-flash","author":"qwen","name":"Qwen3.6 Flash","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":0.1875,"output_per_m":1.125,"unit":null,"unit_price":null,"created":1777248000,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":65536,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","highlights":["Vision","Reasoning","Tools"]},{"id":"qwen/qwen3.6-flash-2026-04-16","author":"qwen","name":"Qwen3.6 Flash","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":0.1875,"output_per_m":1.125,"unit":null,"unit_price":null,"created":1777248000,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":65536,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","highlights":["Vision","Reasoning","Tools"]},{"id":"qwen/qwen3.6-max-preview","author":"qwen","name":"Qwen3.6 Max Preview","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":1.027,"output_per_m":6.162,"unit":null,"unit_price":null,"created":1776643200,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":65536,"description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","highlights":["Reasoning","Tools"]},{"id":"qwen/qwen3.6-plus","author":"qwen","name":"Qwen3.6 Plus","provider":"together","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":0.5,"output_per_m":3,"unit":null,"unit_price":null,"created":1775088000,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":65536,"description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","highlights":["Vision","Reasoning","Tools"]},{"id":"qwen/qwen3.6-plus-2026-04-02","author":"qwen","name":"Qwen3.6 Plus","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":0.325,"output_per_m":1.95,"unit":null,"unit_price":null,"created":1775088000,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":65536,"description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","highlights":["Vision","Reasoning","Tools"]},{"id":"qwen/qwen3.7-flash","author":"qwen","name":"Qwen3.7 Flash","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":0.03,"output_per_m":0.13,"unit":null,"unit_price":null,"created":1784073600,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":131072,"description":"Lightweight multimodal Qwen model for high-throughput text, image, and video tasks","highlights":["Vision","Reasoning","Tools"]},{"id":"qwen/qwen3.7-flash-2026-07-15","author":"qwen","name":"Qwen3.7 Flash","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":0.03,"output_per_m":0.13,"unit":null,"unit_price":null,"created":1784073600,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":131072,"description":"Lightweight multimodal Qwen model for high-throughput text, image, and video tasks","highlights":["Vision","Reasoning","Tools"]},{"id":"qwen/qwen3.7-flash:free","author":"qwen","name":"Qwen3.7 Flash (free)","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":1000000,"input_per_m":0,"output_per_m":0,"unit":null,"unit_price":null,"created":1784073600,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":131072,"description":"Lightweight multimodal Qwen model for high-throughput text, image, and video tasks","highlights":["Free","Vision","Reasoning","Tools"]},{"id":"qwen/qwen3.7-max","author":"qwen","name":"Qwen3.7 Max","provider":"together","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":1.25,"output_per_m":3.75,"unit":null,"unit_price":null,"created":1779321600,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":65536,"description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","highlights":["Reasoning","Tools"]},{"id":"qwen/qwen3.7-max-2026-05-17","author":"qwen","name":"Qwen3.7 Max","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":1.475,"output_per_m":4.425,"unit":null,"unit_price":null,"created":1779321600,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":65536,"description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","highlights":["Reasoning","Tools"]},{"id":"qwen/qwen3.7-max-2026-05-20","author":"qwen","name":"Qwen3.7 Max","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":1.475,"output_per_m":4.425,"unit":null,"unit_price":null,"created":1779321600,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":65536,"description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","highlights":["Reasoning","Tools"]},{"id":"qwen/qwen3.7-max-2026-06-08","author":"qwen","name":"Qwen3.7 Max","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":1.475,"output_per_m":4.425,"unit":null,"unit_price":null,"created":1779321600,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":65536,"description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","highlights":["Reasoning","Tools"]},{"id":"qwen/qwen3.7-max-preview","author":"qwen","name":"Qwen3.7 Max","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":1.475,"output_per_m":4.425,"unit":null,"unit_price":null,"created":1779321600,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":65536,"description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","highlights":["Reasoning","Tools"]},{"id":"qwen/qwen3.7-plus","author":"qwen","name":"Qwen3.7 Plus","provider":"together","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":0.32,"output_per_m":1.28,"unit":null,"unit_price":null,"created":1780358400,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":64000,"description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","highlights":["Vision","Reasoning","Tools"]},{"id":"qwen/qwen3.7-plus-2026-05-26","author":"qwen","name":"Qwen3.7 Plus","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":0.32,"output_per_m":1.28,"unit":null,"unit_price":null,"created":1780358400,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":64000,"description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","highlights":["Vision","Reasoning","Tools"]},{"id":"qwen/qwen3.8-2.4t-a95b","author":"qwen","name":"Qwen3.8 2.4T A95B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1048576,"input_per_m":2,"output_per_m":6,"unit":null,"unit_price":null,"created":1786492800,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":131072,"description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","highlights":["Vision","Reasoning","Tools"]},{"id":"qwen/qwen3.8-27b","author":"qwen","name":"Qwen3.8 27B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.2,"output_per_m":2.5,"unit":null,"unit_price":null,"created":1786665600,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":32768,"description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","highlights":["Vision","Reasoning","Tools"]},{"id":"qwen/qwq-32b","author":"qwen","name":"QwQ 32B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.15,"output_per_m":0.4,"unit":null,"unit_price":null,"created":1733011200,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":8192,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","highlights":["Reasoning","Tools"]},{"id":"qwen/qwq-32b-preview","author":"qwen","name":"QwQ 32B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.12,"output_per_m":0.18,"unit":null,"unit_price":null,"variants":["free"],"created":1733011200,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":8192,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","highlights":["Reasoning","Tools"]},{"id":"qwen/qwq-32b:free","author":"qwen","name":"QwQ 32B (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":131072,"input_per_m":0,"output_per_m":0,"unit":null,"unit_price":null,"variants":["free"],"created":1733011200,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":8192,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","highlights":["Free","Reasoning","Tools"]},{"id":"qwen/qwq-plus","author":"qwen","name":"QwQ Plus","provider":"qwen","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.8,"output_per_m":2.4,"unit":null,"unit_price":null,"created":1741132800,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":8192,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","highlights":["Reasoning","Tools"]},{"id":"sao10k/l3-70b-euryale-v2.1","author":"sao10k","name":"L3 70B Euryale V2.1","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.7,"output_per_m":0.8,"unit":null,"unit_price":null,"highlights":[]},{"id":"sao10k/l3-8b-lunaris-v1","author":"sao10k","name":"L3 8B Lunaris V1","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.03,"output_per_m":0.06,"unit":null,"unit_price":null,"variants":["free"],"highlights":[]},{"id":"sao10k/l3-8b-lunaris-v1-turbo","author":"sao10k","name":"L3 8B Lunaris V1 Turbo","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.04,"output_per_m":0.05,"unit":null,"unit_price":null,"variants":["free"],"highlights":[]},{"id":"sao10k/l3-8b-lunaris-v1:free","author":"sao10k","name":"L3 8B Lunaris V1 (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":null,"input_per_m":0,"output_per_m":0,"unit":null,"unit_price":null,"variants":["free"],"highlights":["Free"]},{"id":"sao10k/l3.1-70b-euryale-v2.2","author":"sao10k","name":"Llama 3.1 70B Euryale","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":20480,"input_per_m":0.85,"output_per_m":0.85,"unit":null,"unit_price":null,"created":1704067200,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":16384,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","highlights":[]},{"id":"sao10k/l3.3-70b-euryale-v2.3","author":"sao10k","name":"Llama 3.3 70B Euryale","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":20480,"input_per_m":0.85,"output_per_m":0.85,"unit":null,"unit_price":null,"created":1704067200,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":16384,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","highlights":[]},{"id":"sarvam/sarvam-105b","author":"sarvam","name":"Sarvam 105B","provider":"sarvam","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.36,"output_per_m":0.9,"unit":null,"unit_price":null,"created":1756684800,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":131072,"description":"Flagship Indian-language reasoning model for enterprise multilingual applications","highlights":["Reasoning","Tools"]},{"id":"sarvam/sarvam-105b-conversations","author":"sarvam","name":"Sarvam 105B Conversations","provider":"sarvam","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":null,"input_per_m":0.36,"output_per_m":0.9,"unit":null,"unit_price":null,"highlights":[]},{"id":"sentence-transformers/all-minilm-l12-v2","author":"sentence-transformers","name":"All Minilm L12 V2","provider":"deepinfra","status":"live","blocked_by":null,"kind":"embedding","free_kind":null,"context":null,"input_per_m":0.005,"output_per_m":null,"unit":null,"unit_price":null,"highlights":[]},{"id":"sentence-transformers/all-minilm-l6-v2","author":"sentence-transformers","name":"All Minilm L6 V2","provider":"deepinfra","status":"live","blocked_by":null,"kind":"embedding","free_kind":null,"context":null,"input_per_m":0.005,"output_per_m":null,"unit":null,"unit_price":null,"highlights":[]},{"id":"sentence-transformers/all-mpnet-base-v2","author":"sentence-transformers","name":"All Mpnet Base V2","provider":"deepinfra","status":"live","blocked_by":null,"kind":"embedding","free_kind":null,"context":null,"input_per_m":0.005,"output_per_m":null,"unit":null,"unit_price":null,"highlights":[]},{"id":"sentence-transformers/clip-vit-b-32","author":"sentence-transformers","name":"Clip Vit B 32","provider":"deepinfra","status":"live","blocked_by":null,"kind":"embedding","free_kind":null,"context":null,"input_per_m":0.005,"output_per_m":null,"unit":null,"unit_price":null,"highlights":[]},{"id":"sentence-transformers/clip-vit-b-32-multilingual-v1","author":"sentence-transformers","name":"Clip Vit B 32 Multilingual V1","provider":"deepinfra","status":"live","blocked_by":null,"kind":"embedding","free_kind":null,"context":null,"input_per_m":0.005,"output_per_m":null,"unit":null,"unit_price":null,"highlights":[]},{"id":"sentence-transformers/multi-qa-mpnet-base-dot-v1","author":"sentence-transformers","name":"Multi-QA-mpnet-base-dot-v1","provider":"deepinfra","status":"live","blocked_by":null,"kind":"embedding","free_kind":null,"context":512,"input_per_m":0.005,"output_per_m":null,"unit":null,"unit_price":null,"created":1630281600,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":768,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","highlights":[]},{"id":"sentence-transformers/paraphrase-minilm-l6-v2","author":"sentence-transformers","name":"Paraphrase Minilm L6 V2","provider":"deepinfra","status":"live","blocked_by":null,"kind":"embedding","free_kind":null,"context":null,"input_per_m":0.005,"output_per_m":null,"unit":null,"unit_price":null,"highlights":[]},{"id":"shibing624/text2vec-base-chinese","author":"shibing624","name":"Text2vec Base Chinese","provider":"deepinfra","status":"live","blocked_by":null,"kind":"embedding","free_kind":null,"context":null,"input_per_m":0.005,"output_per_m":null,"unit":null,"unit_price":null,"highlights":[]},{"id":"stepfun/step-3.5-flash","author":"stepfun","name":"Step 3.5 Flash","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":256000,"input_per_m":0.09,"output_per_m":0.3,"unit":null,"unit_price":null,"variants":["free"],"created":1769644800,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":256000,"description":"StepFun flash lane for quick multimodal reasoning and coding assistance","highlights":["Reasoning","Tools"]},{"id":"stepfun/step-3.5-flash:free","author":"stepfun","name":"Step 3.5 Flash (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":256000,"input_per_m":0,"output_per_m":0,"unit":null,"unit_price":null,"variants":["free"],"created":1769644800,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":256000,"description":"StepFun flash lane for quick multimodal reasoning and coding assistance","highlights":["Free","Reasoning","Tools"]},{"id":"stepfun/step-3.7-flash","author":"stepfun","name":"Step 3.7 Flash","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":256000,"input_per_m":0.2,"output_per_m":1.15,"unit":null,"unit_price":null,"created":1780012800,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":256000,"description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","highlights":["Vision","Reasoning","Tools"]},{"id":"tencent/hy3","author":"tencent","name":"Tencent Hy3","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":262144,"input_per_m":0.14,"output_per_m":0.58,"unit":null,"unit_price":null,"created":1783296000,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":false,"audio":false},"max_output":128000,"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","highlights":["Reasoning","Tools"]},{"id":"thenlper/gte-base","author":"thenlper","name":"Gte Base","provider":"deepinfra","status":"live","blocked_by":null,"kind":"embedding","free_kind":null,"context":null,"input_per_m":0.005,"output_per_m":null,"unit":null,"unit_price":null,"highlights":[]},{"id":"thenlper/gte-large","author":"thenlper","name":"Gte Large","provider":"deepinfra","status":"live","blocked_by":null,"kind":"embedding","free_kind":null,"context":null,"input_per_m":0.01,"output_per_m":null,"unit":null,"unit_price":null,"highlights":[]},{"id":"thinkingmachines/inkling","author":"thinkingmachines","name":"Inkling","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":65536,"input_per_m":0.95,"output_per_m":4.05,"unit":null,"unit_price":null,"created":1784073600,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":65536,"description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","highlights":["Vision","Reasoning","Tools"]},{"id":"thinkingmachines/inkling-small","author":"thinkingmachines","name":"Inkling Small","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":524288,"input_per_m":0.45,"output_per_m":1.2,"unit":null,"unit_price":null,"created":1785369600,"variant":"thinking","reasoning":true,"input_modalities":["text","image","audio"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":true},"max_output":1048576,"description":"Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio","highlights":["Vision","Reasoning","Tools"]},{"id":"x-ai/grok-4.20","author":"x-ai","name":"Grok 4.20","provider":"xai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":2000000,"input_per_m":1.25,"output_per_m":2.5,"unit":null,"unit_price":null,"created":1774915200,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":1800000,"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","highlights":["Longest context","Vision","Reasoning","Tools"]},{"id":"x-ai/grok-4.20-non-reasoning","author":"x-ai","name":"Grok 4.20 Non-Reasoning","provider":"xai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":2000000,"input_per_m":1.25,"output_per_m":2.5,"unit":null,"unit_price":null,"created":1773100800,"variant":"standard","reasoning":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":2000000,"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","highlights":["Longest context","Vision","Tools"]},{"id":"x-ai/grok-4.3","author":"x-ai","name":"Grok 4.3","provider":"xai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":1.25,"output_per_m":2.5,"unit":null,"unit_price":null,"created":1776384000,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":30000,"description":"xAI's Grok for chat, coding, agentic tools, and lower hallucination risk","highlights":["Vision","Reasoning","Tools"]},{"id":"x-ai/grok-4.5","author":"x-ai","name":"Grok 4.5","provider":"xai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":500000,"input_per_m":2,"output_per_m":6,"unit":null,"unit_price":null,"created":1783468800,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":500000,"description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","highlights":["Vision","Reasoning","Tools"]},{"id":"x-ai/grok-4.6","author":"x-ai","name":"Grok 4.6","provider":"xai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":500000,"input_per_m":2,"output_per_m":6,"unit":null,"unit_price":null,"created":1786492800,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":500000,"description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","highlights":["Vision","Reasoning","Tools"]},{"id":"x-ai/grok-4.7","author":"x-ai","name":"Grok 4.7","provider":"xai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":500000,"input_per_m":2,"output_per_m":6,"unit":null,"unit_price":null,"created":1789948800,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":500000,"description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","highlights":["Vision","Reasoning","Tools"]},{"id":"x-ai/grok-build-0.1","author":"x-ai","name":"Grok Build 0.1","provider":"xai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":256000,"input_per_m":1,"output_per_m":2,"unit":null,"unit_price":null,"created":1776297600,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":256000,"description":"Fast Grok coding model tuned for agentic engineering and iterative edits","highlights":["Vision","Reasoning","Tools"]},{"id":"xiaomi/mimo-v2.5","author":"xiaomi","name":"MiMo-V2.5","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1048576,"input_per_m":0.4,"output_per_m":2,"unit":null,"unit_price":null,"created":1776816000,"variant":"thinking","reasoning":true,"input_modalities":["text","image","audio","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":true},"max_output":131072,"description":"Open MiMo model for multimodal coding agents and long-context automation","highlights":["Vision","Reasoning","Tools"]},{"id":"xiaomi/mimo-v2.5-pro","author":"xiaomi","name":"MiMo-V2.5-Pro","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1048576,"input_per_m":1,"output_per_m":3,"unit":null,"unit_price":null,"created":1776816000,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":131072,"description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","highlights":["Reasoning","Tools"]},{"id":"z-ai/glm-4.5","author":"z-ai","name":"GLM-4.5","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.38,"output_per_m":1.6,"unit":null,"unit_price":null,"created":1753660800,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":98304,"description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","highlights":["Reasoning","Tools"]},{"id":"z-ai/glm-4.5-air","author":"z-ai","name":"GLM-4.5-Air","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":131072,"input_per_m":0.2,"output_per_m":1.1,"unit":null,"unit_price":null,"created":1753660800,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":98304,"description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","highlights":["Reasoning","Tools"]},{"id":"z-ai/glm-4.6","author":"z-ai","name":"GLM-4.6","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":204800,"input_per_m":0.5,"output_per_m":2,"unit":null,"unit_price":null,"created":1759190400,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":131072,"description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","highlights":["Reasoning","Tools"]},{"id":"z-ai/glm-4.6v","author":"z-ai","name":"GLM-4.6V","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":128000,"input_per_m":0.3,"output_per_m":0.9,"unit":null,"unit_price":null,"created":1765152000,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":32768,"description":"GLM vision model for visual reasoning, documents, and multimodal agents","highlights":["Vision","Reasoning","Tools"]},{"id":"z-ai/glm-4.7","author":"z-ai","name":"GLM-4.7","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":204800,"input_per_m":0.4,"output_per_m":1.75,"unit":null,"unit_price":null,"created":1766361600,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":131072,"description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","highlights":["Reasoning","Tools"]},{"id":"z-ai/glm-4.7-flash","author":"z-ai","name":"GLM-4.7-Flash","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":200000,"input_per_m":0.06,"output_per_m":0.4,"unit":null,"unit_price":null,"created":1768780800,"variant":"standard","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":131072,"description":"Budget GLM lane for fast coding help, routing, and everyday automation","highlights":["Reasoning","Tools"]},{"id":"z-ai/glm-4.7-flash:free","author":"z-ai","name":"GLM-4.7-Flash (free)","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":"sponsored","context":200000,"input_per_m":0,"output_per_m":0,"unit":null,"unit_price":null,"variants":["free"],"created":1768780800,"variant":"standard","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":131072,"description":"Budget GLM lane for fast coding help, routing, and everyday automation","highlights":["Free","Reasoning","Tools"]},{"id":"z-ai/glm-5","author":"z-ai","name":"GLM-5","provider":"zai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":204800,"input_per_m":1,"output_per_m":3.2,"unit":null,"unit_price":null,"created":1770854400,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":false,"reasoning":true,"vision":false,"audio":false},"max_output":131072,"description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","highlights":["Reasoning","Tools"]},{"id":"z-ai/glm-5-turbo","author":"z-ai","name":"GLM-5-Turbo","provider":"zai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":200000,"input_per_m":1.2,"output_per_m":4,"unit":null,"unit_price":null,"created":1773619200,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":false,"audio":false},"max_output":131072,"description":"Faster GLM-5 lane for coding agents that need lower latency","highlights":["Reasoning","Tools"]},{"id":"z-ai/glm-5.1","author":"z-ai","name":"GLM-5.1","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":200000,"input_per_m":1.05,"output_per_m":3.5,"unit":null,"unit_price":null,"created":1775520000,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":false,"audio":false},"max_output":131072,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","highlights":["Reasoning","Tools"]},{"id":"z-ai/glm-5.2","author":"z-ai","name":"GLM-5.2","provider":"deepinfra","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":0.75,"output_per_m":2.4,"unit":null,"unit_price":null,"created":1781308800,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":false,"audio":false},"max_output":131072,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","highlights":["Reasoning","Tools"]},{"id":"z-ai/glm-5.3","author":"z-ai","name":"GLM-5.3","provider":"zai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":0.079,"output_per_m":4.8,"unit":null,"unit_price":null,"created":1786665600,"variant":"thinking","reasoning":true,"input_modalities":["text"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":false,"audio":false},"max_output":131072,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","highlights":["Reasoning","Tools"]},{"id":"z-ai/glm-5.3-flash","author":"z-ai","name":"GLM-5.3-Flash","provider":"zai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":0.01206,"output_per_m":0.9,"unit":null,"unit_price":null,"created":1787702400,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":131072,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","highlights":["Vision","Reasoning","Tools"]},{"id":"z-ai/glm-5.3-flashx","author":"z-ai","name":"GLM-5.3-FlashX","provider":"zai","status":"live","blocked_by":null,"kind":"chat","free_kind":null,"context":1000000,"input_per_m":0.37,"output_per_m":1.25,"unit":null,"unit_price":null,"created":1789689600,"variant":"thinking","reasoning":true,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"],"capabilities":{"tools":true,"json":true,"reasoning":true,"vision":true,"audio":false},"max_output":131072,"description":"High-speed GLM-5.3-Flash serving option for coding and agent workflows","highlights":["Vision","Reasoning","Tools"]},{"id":"google/gemini-2.5-flash-image","author":"google","name":"Nano Banana","provider":"google","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":32768,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.04,"created":1756166400,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text","image"],"capabilities":{"tools":false,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":32768,"description":"Nano Banana image model for fast generation, edits, and character-consistent assets","highlights":["Vision","Reasoning"]},{"id":"google/gemini-3-pro-image","author":"google","name":"Nano Banana Pro","provider":"google","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":131072,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.08,"created":1763596800,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text","image"],"capabilities":{"tools":false,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":32768,"description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","highlights":["Vision","Reasoning"]},{"id":"google/gemini-3.1-flash-image","author":"google","name":"Nano Banana 2","provider":"google","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":65536,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.04,"created":1772064000,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text","image"],"capabilities":{"tools":false,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":65536,"description":"Image model for prompt-driven generation, editing, and visual design workflows","highlights":["Vision","Reasoning"]},{"id":"google/gemini-3-pro-image-preview","author":"google","name":"Nano Banana Pro","provider":"google","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":131072,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.08,"created":1763596800,"variant":"thinking","reasoning":true,"input_modalities":["text","image"],"output_modalities":["text","image"],"capabilities":{"tools":false,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":32768,"description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","highlights":["Vision","Reasoning"]},{"id":"google/gemini-3.1-flash-image-preview","author":"google","name":"Nano Banana 2","provider":"google","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":65536,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.04,"created":1772064000,"variant":"thinking","reasoning":true,"input_modalities":["text","image","pdf"],"output_modalities":["text","image"],"capabilities":{"tools":false,"json":false,"reasoning":true,"vision":true,"audio":false},"max_output":65536,"description":"Image model for prompt-driven generation, editing, and visual design workflows","highlights":["Vision","Reasoning"]},{"id":"x-ai/grok-imagine-image","author":"x-ai","name":"Grok Imagine Image","provider":"xai","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":16000,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.02,"created":1769558400,"variant":"standard","reasoning":false,"input_modalities":["text","image","pdf"],"output_modalities":["image","pdf"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":0,"description":"Image model for prompt-driven generation, editing, and visual design workflows","highlights":["Vision"]},{"id":"x-ai/grok-imagine-image-2.0","author":"x-ai","name":"Grok Imagine Image 2.0","provider":"xai","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":8000,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.04,"created":1786060800,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["image"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":0,"description":"Image model for prompt-driven generation, editing, and visual design workflows","highlights":["Vision"]},{"id":"x-ai/grok-imagine-image-quality","author":"x-ai","name":"Grok Imagine Image Quality","provider":"xai","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.05,"highlights":[]},{"id":"black-forest-labs/flux.1-schnell","author":"black-forest-labs","name":"FLUX.1-schnell","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":77,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.0005,"created":1722470400,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["image"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":0,"description":"Image model for prompt-driven generation, editing, and visual design workflows","highlights":[]},{"id":"black-forest-labs/flux.1-kontext-pro","author":"black-forest-labs","name":"FLUX.1 Kontext Pro","provider":"together","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.042,"highlights":[]},{"id":"black-forest-labs/flux.1-kontext-max","author":"black-forest-labs","name":"FLUX.1 Kontext Max","provider":"together","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.084,"highlights":[]},{"id":"black-forest-labs/flux.1.1-pro","author":"black-forest-labs","name":"FLUX.1.1 Pro","provider":"together","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.042,"highlights":[]},{"id":"black-forest-labs/flux.2-dev","author":"black-forest-labs","name":"FLUX.2 Dev","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.01,"highlights":[]},{"id":"black-forest-labs/flux.2-flex","author":"black-forest-labs","name":"FLUX.2 Flex","provider":"together","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.03,"highlights":[]},{"id":"black-forest-labs/flux.2-pro","author":"black-forest-labs","name":"FLUX.2 Pro","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.015,"highlights":[]},{"id":"black-forest-labs/flux.2-max","author":"black-forest-labs","name":"FLUX.2 Max","provider":"together","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.074,"highlights":[]},{"id":"openai/gpt-image-1.5","author":"openai","name":"GPT Image 1.5","provider":"together","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.199,"highlights":[]},{"id":"openai/gpt-image-2","author":"openai","name":"GPT-Image-2","provider":"together","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":272000,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.165,"created":1776729600,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["image"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":16384,"description":"Image model for prompt-driven generation, editing, and visual design workflows","highlights":["Vision"]},{"id":"wan-ai/wan2.6-image","author":"wan-ai","name":"Wan2.6 Image","provider":"together","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.03,"highlights":[]},{"id":"bytedance/seedream-3.0","author":"bytedance","name":"Seedream 3.0","provider":"together","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.018,"highlights":[]},{"id":"bytedance/seedream-4.0","author":"bytedance","name":"Seedream 4.0","provider":"together","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.03,"highlights":[]},{"id":"bytedance/seedream-5.0-lite","author":"bytedance","name":"Seedream 5.0 Lite","provider":"together","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.035,"highlights":[]},{"id":"rundiffusion/juggernaut-lightning-flux","author":"rundiffusion","name":"Juggernaut Lightning FLUX","provider":"together","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.002,"highlights":[]},{"id":"rundiffusion/juggernaut-pro-flux","author":"rundiffusion","name":"Juggernaut Pro FLUX","provider":"together","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.005,"highlights":[]},{"id":"ideogram/ideogram-3.0","author":"ideogram","name":"Ideogram 3.0","provider":"together","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.06,"highlights":[]},{"id":"ideogram/ideogram-4.0","author":"ideogram","name":"Ideogram 4.0","provider":"together","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.1,"highlights":[]},{"id":"stabilityai/stable-diffusion-xl","author":"stabilityai","name":"Stable Diffusion XL","provider":"together","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.002,"highlights":[]},{"id":"google/flash-image-3.1-lite","author":"google","name":"Flash Image 3.1 Lite","provider":"together","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.069,"highlights":[]},{"id":"qwen/qwen-image","author":"qwen","name":"Qwen-Image","provider":"together","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":8192,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.006,"created":1772323200,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["image"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":4096,"description":"Image model for prompt-driven generation, editing, and visual design workflows","highlights":[]},{"id":"qwen/qwen-image-2.0","author":"qwen","name":"Qwen Image 2.0","provider":"together","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":8192,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.035,"created":1772496000,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["image"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":0,"description":"Image model for prompt-driven generation, editing, and visual design workflows","highlights":[]},{"id":"qwen/qwen-image-2.0-pro","author":"qwen","name":"Qwen Image 2.0 Pro","provider":"together","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":8192,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.075,"created":1772496000,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["image"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":0,"description":"Image model for prompt-driven generation, editing, and visual design workflows","highlights":[]},{"id":"prunaai/p-image-ideogram","author":"prunaai","name":"P Image Ideogram","provider":"together","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.003,"highlights":[]},{"id":"openai/gpt-image-1","author":"openai","name":"GPT Image 1","provider":"openai","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.167,"highlights":[]},{"id":"openai/gpt-image-1.5-direct","author":"openai","name":"GPT Image 1.5 Direct","provider":"openai","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.199,"highlights":[]},{"id":"openai/gpt-image-2-direct","author":"openai","name":"GPT Image 2 Direct","provider":"openai","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.165,"highlights":[]},{"id":"openai/tts-1","author":"openai","name":"TTS 1","provider":"openai","status":"live","blocked_by":null,"kind":"tts","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"char","unit_price":0.000015,"highlights":[]},{"id":"openai/tts-1-hd","author":"openai","name":"TTS 1 HD","provider":"openai","status":"live","blocked_by":null,"kind":"tts","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"char","unit_price":0.00003,"highlights":[]},{"id":"openai/whisper-1","author":"openai","name":"Whisper 1","provider":"openai","status":"live","blocked_by":null,"kind":"stt","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"minute","unit_price":0.006,"highlights":[]},{"id":"elevenlabs/eleven-v4","author":"elevenlabs","name":"Eleven V4","provider":"elevenlabs","status":"live","blocked_by":null,"kind":"tts","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"char","unit_price":0.00008,"highlights":[]},{"id":"elevenlabs/eleven-v4-turbo","author":"elevenlabs","name":"Eleven V4 Turbo","provider":"elevenlabs","status":"live","blocked_by":null,"kind":"tts","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"char","unit_price":0.00004,"highlights":[]},{"id":"elevenlabs/eleven-v3","author":"elevenlabs","name":"Eleven V3","provider":"elevenlabs","status":"live","blocked_by":null,"kind":"tts","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"char","unit_price":0.00008,"highlights":[]},{"id":"elevenlabs/eleven-v3-conversational","author":"elevenlabs","name":"Eleven V3 Conversational","provider":"elevenlabs","status":"live","blocked_by":null,"kind":"tts","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"char","unit_price":0.00004,"highlights":[]},{"id":"elevenlabs/eleven-multilingual-v2","author":"elevenlabs","name":"Eleven Multilingual V2","provider":"elevenlabs","status":"live","blocked_by":null,"kind":"tts","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"char","unit_price":0.00008,"highlights":[]},{"id":"elevenlabs/eleven-flash-v2.5","author":"elevenlabs","name":"Eleven Flash V2.5","provider":"elevenlabs","status":"live","blocked_by":null,"kind":"tts","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"char","unit_price":0.00004,"highlights":[]},{"id":"elevenlabs/eleven-turbo-v2.5","author":"elevenlabs","name":"Eleven Turbo V2.5","provider":"elevenlabs","status":"live","blocked_by":null,"kind":"tts","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"char","unit_price":0.00004,"highlights":[]},{"id":"elevenlabs/eleven-flash-v2","author":"elevenlabs","name":"Eleven Flash V2","provider":"elevenlabs","status":"live","blocked_by":null,"kind":"tts","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"char","unit_price":0.00004,"highlights":[]},{"id":"elevenlabs/eleven-turbo-v2","author":"elevenlabs","name":"Eleven Turbo V2","provider":"elevenlabs","status":"live","blocked_by":null,"kind":"tts","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"char","unit_price":0.00004,"highlights":[]},{"id":"elevenlabs/scribe-v2","author":"elevenlabs","name":"Scribe V2","provider":"elevenlabs","status":"live","blocked_by":null,"kind":"stt","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"minute","unit_price":0.0036666666666666666,"highlights":[]},{"id":"elevenlabs/scribe-v2-medical","author":"elevenlabs","name":"Scribe V2 Medical","provider":"elevenlabs","status":"live","blocked_by":null,"kind":"stt","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"minute","unit_price":0.0036666666666666666,"highlights":[]},{"id":"hexgrad/kokoro-82m","author":"hexgrad","name":"Kokoro 82M","provider":"together","status":"live","blocked_by":null,"kind":"tts","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"char","unit_price":0.000004,"highlights":[]},{"id":"canopylabs/orpheus-3b","author":"canopylabs","name":"Orpheus 3B","provider":"together","status":"live","blocked_by":null,"kind":"tts","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"char","unit_price":0.000015,"highlights":[]},{"id":"cartesia/sonic-2","author":"cartesia","name":"Sonic 2","provider":"together","status":"live","blocked_by":null,"kind":"tts","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"char","unit_price":0.000065,"highlights":[]},{"id":"cartesia/sonic-3","author":"cartesia","name":"Sonic 3","provider":"together","status":"live","blocked_by":null,"kind":"tts","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"char","unit_price":0.000065,"highlights":[]},{"id":"openai/whisper-large-v3","author":"openai","name":"Whisper 3 Large","provider":"together","status":"live","blocked_by":null,"kind":"stt","edit":false,"free_kind":null,"context":448,"input_per_m":null,"output_per_m":null,"unit":"minute","unit_price":0.0015,"created":1727740800,"variant":"standard","reasoning":false,"input_modalities":["audio"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":true},"max_output":4096,"description":"Open Whisper checkpoint for robust multilingual transcription and captioning","highlights":[]},{"id":"nvidia/parakeet-tdt-0.6b","author":"nvidia","name":"Parakeet Tdt 0.6B","provider":"together","status":"live","blocked_by":null,"kind":"stt","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"minute","unit_price":0.0015,"highlights":[]},{"id":"sarvam/bulbul-v3","author":"sarvam","name":"Bulbul V3","provider":"sarvam","status":"live","blocked_by":null,"kind":"tts","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"char","unit_price":0.000002,"highlights":[]},{"id":"sarvam/mayura","author":"sarvam","name":"Mayura","provider":"sarvam","status":"live","blocked_by":null,"kind":"translate","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"char","unit_price":0.000002,"highlights":[]},{"id":"sarvam/saarika-v2","author":"sarvam","name":"Saarika V2","provider":"sarvam","status":"live","blocked_by":null,"kind":"stt","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"request","unit_price":0.01,"highlights":[]},{"id":"x-ai/grok-imagine-video","author":"x-ai","name":"Grok Imagine Video","provider":"xai","status":"live","blocked_by":null,"kind":"video","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"video","unit_price":0.25,"highlights":[]},{"id":"x-ai/grok-imagine-video-1.5","author":"x-ai","name":"Grok Imagine Video 1.5","provider":"xai","status":"live","blocked_by":null,"kind":"video","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"video","unit_price":0.4,"highlights":[]},{"id":"openai/sora-2","author":"openai","name":"Sora 2","provider":"openai","status":"live","blocked_by":null,"kind":"video","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"video","unit_price":0.8,"highlights":[]},{"id":"openai/sora-2-pro","author":"openai","name":"Sora 2 Pro","provider":"openai","status":"live","blocked_by":null,"kind":"video","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"video","unit_price":4,"highlights":[]},{"id":"google/veo-3.1-fast","author":"google","name":"Veo 3.1 Fast","provider":"google","status":"live","blocked_by":null,"kind":"video","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"video","unit_price":1.5,"highlights":[]},{"id":"google/veo-3.1","author":"google","name":"Veo 3.1","provider":"google","status":"live","blocked_by":null,"kind":"video","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"video","unit_price":2.5,"highlights":[]},{"id":"xiaomimimo/mimo-v2.5-tts","author":"xiaomimimo","name":"MiMo-V2.5-TTS","provider":"deepinfra","status":"live","blocked_by":null,"kind":"tts","edit":false,"free_kind":"always","context":8192,"input_per_m":null,"output_per_m":null,"unit":"char","unit_price":0,"created":1776816000,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["audio"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":8192,"description":"Speech generation model for controllable voice, narration, and audio delivery","highlights":["Always free"]},{"id":"xiaomimimo/mimo-v2.5-tts-voicedesign","author":"xiaomimimo","name":"MiMo-V2.5-TTS-VoiceDesign","provider":"deepinfra","status":"live","blocked_by":null,"kind":"tts","edit":false,"free_kind":"always","context":8192,"input_per_m":null,"output_per_m":null,"unit":"char","unit_price":0,"created":1776816000,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["audio"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":8192,"description":"Speech generation model for controllable voice, narration, and audio delivery","highlights":["Always free"]},{"id":"stabilityai/stable-diffusion-xl:free","author":"stabilityai","name":"Stable Diffusion XL (free)","provider":"together","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":"sponsored","context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0,"highlights":["Free"]},{"id":"rundiffusion/juggernaut-lightning-flux:free","author":"rundiffusion","name":"Juggernaut Lightning FLUX (free)","provider":"together","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":"sponsored","context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0,"highlights":["Free"]},{"id":"fastvideo/fastwan-qad-fp8-1.3b","author":"fastvideo","name":"Fastwan Qad FP8 1.3B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"video","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"video","unit_price":0.0125,"highlights":[]},{"id":"prunaai/p-video","author":"prunaai","name":"P Video","provider":"deepinfra","status":"live","blocked_by":null,"kind":"video","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"video","unit_price":0.1,"highlights":[]},{"id":"pixverse/pixverse-6-t2v","author":"pixverse","name":"PixVerse 6 T2V","provider":"deepinfra","status":"live","blocked_by":null,"kind":"video","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"video","unit_price":0.225,"highlights":[]},{"id":"wan-ai/wan2.2-t2v-a14b","author":"wan-ai","name":"Wan2.2-T2V-A14B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"video","edit":false,"free_kind":null,"context":100,"input_per_m":null,"output_per_m":null,"unit":"video","unit_price":0.375,"created":1753660800,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["video"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":1,"description":"Video model for prompt-guided generation, editing, and motion workflows","highlights":[]},{"id":"wan-ai/wan2.6-t2v","author":"wan-ai","name":"Wan2.6 T2V","provider":"deepinfra","status":"live","blocked_by":null,"kind":"video","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"video","unit_price":0.5,"highlights":[]},{"id":"google/veo-3.0-fast","author":"google","name":"Veo 3.0 Fast","provider":"deepinfra","status":"live","blocked_by":null,"kind":"video","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"video","unit_price":0.75,"highlights":[]},{"id":"google/veo-3.0","author":"google","name":"Veo 3.0","provider":"deepinfra","status":"live","blocked_by":null,"kind":"video","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"video","unit_price":2,"highlights":[]},{"id":"bria/enhance","author":"bria","name":"Enhance","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":true,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.04,"highlights":[]},{"id":"prunaai/p-image-edit","author":"prunaai","name":"P Image Edit","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":true,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.01,"highlights":[]},{"id":"qwen/qwen-image-edit-max","author":"qwen","name":"Qwen Image Edit Max","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":true,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.075,"highlights":[]},{"id":"stabilityai/sd3.5-medium","author":"stabilityai","name":"Sd3.5 Medium","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.03,"highlights":[]},{"id":"stabilityai/sd3.5","author":"stabilityai","name":"Sd3.5","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.06,"highlights":[]},{"id":"bria/erase_foreground","author":"bria","name":"Erase Foreground","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":true,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.04,"highlights":[]},{"id":"bria/expand","author":"bria","name":"Expand","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":true,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.04,"highlights":[]},{"id":"bria/gen_fill","author":"bria","name":"Gen Fill","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":true,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.04,"highlights":[]},{"id":"bria/bria-3.2","author":"bria","name":"Bria 3.2","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.04,"highlights":[]},{"id":"bria/remove_background","author":"bria","name":"Remove Background","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":true,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.018,"highlights":[]},{"id":"black-forest-labs/flux-1-dev","author":"black-forest-labs","name":"FLUX.1-dev","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":4096,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.009,"created":1722470400,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["image"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":0,"description":"Image model for prompt-driven generation, editing, and visual design workflows","highlights":[]},{"id":"bria/erase","author":"bria","name":"Erase","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":true,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.04,"highlights":[]},{"id":"bria/fibo_edit","author":"bria","name":"Fibo Edit","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":true,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.04,"highlights":[]},{"id":"black-forest-labs/flux-2-klein-4b","author":"black-forest-labs","name":"FLUX.2 Klein 4B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":128000,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.014,"created":1768348800,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["image"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":128000,"description":"Image model for prompt-driven generation, editing, and visual design workflows","highlights":[]},{"id":"qwen/qwen-image-edit","author":"qwen","name":"Qwen Image Edit","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":true,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.075,"highlights":[]},{"id":"bria/blur_background","author":"bria","name":"Blur Background","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":true,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.04,"highlights":[]},{"id":"black-forest-labs/flux.1-kontext-dev","author":"black-forest-labs","name":"FLUX.1-Kontext-dev","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":true,"free_kind":null,"context":40960,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.018,"created":1754956800,"variant":"standard","reasoning":false,"input_modalities":["text","image"],"output_modalities":["image"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":true,"audio":false},"max_output":40960,"description":"Image model for prompt-driven generation, editing, and visual design workflows","highlights":["Vision"]},{"id":"bria/replace_background","author":"bria","name":"Replace Background","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":true,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.04,"highlights":[]},{"id":"wan-ai/wan2.7-image-edit","author":"wan-ai","name":"Wan2.7 Image Edit","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":true,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.03,"highlights":[]},{"id":"bytedance/seedream-4","author":"bytedance","name":"Seedream 4","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.04,"highlights":[]},{"id":"clarityai/crystal","author":"clarityai","name":"Crystal","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":true,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.05,"highlights":[]},{"id":"wan-ai/wan2.6-image-edit","author":"wan-ai","name":"Wan2.6 Image Edit","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":true,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.03,"highlights":[]},{"id":"bria/fibo","author":"bria","name":"Fibo","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.04,"highlights":[]},{"id":"stabilityai/sdxl-turbo","author":"stabilityai","name":"SDXL Turbo","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.0002,"highlights":[]},{"id":"qwen/qwen-image-max","author":"qwen","name":"Qwen-Image","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":8192,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.075,"created":1772323200,"variant":"standard","reasoning":false,"input_modalities":["text"],"output_modalities":["image"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":false},"max_output":4096,"description":"Image model for prompt-driven generation, editing, and visual design workflows","highlights":[]},{"id":"clarityai/flux","author":"clarityai","name":"FLUX","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":true,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.2,"highlights":[]},{"id":"prunaai/p-image","author":"prunaai","name":"P Image","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.005,"highlights":[]},{"id":"bytedance/seedream-4.5","author":"bytedance","name":"Seedream 4.5","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.04,"highlights":[]},{"id":"clarityai/creative","author":"clarityai","name":"Creative","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":true,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.05,"highlights":[]},{"id":"run-diffusion/juggernaut-flux","author":"run-diffusion","name":"Juggernaut FLUX","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.009,"highlights":[]},{"id":"wan-ai/wan2.6-t2i","author":"wan-ai","name":"Wan2.6 T2i","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.03,"highlights":[]},{"id":"bria/bria-3.2-vector","author":"bria","name":"Bria 3.2 Vector","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.04,"highlights":[]},{"id":"black-forest-labs/flux-1-redux-dev","author":"black-forest-labs","name":"FLUX 1 Redux Dev","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":true,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.012,"highlights":[]},{"id":"black-forest-labs/flux-2-klein-9b","author":"black-forest-labs","name":"FLUX 2 Klein 9B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"image","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"image","unit_price":0.015,"highlights":[]},{"id":"resembleai/chatterbox-multilingual","author":"resembleai","name":"Chatterbox Multilingual","provider":"deepinfra","status":"live","blocked_by":null,"kind":"tts","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"char","unit_price":0.000001,"highlights":[]},{"id":"canopylabs/orpheus-3b-0.1-ft","author":"canopylabs","name":"Orpheus 3B 0.1 Ft","provider":"deepinfra","status":"live","blocked_by":null,"kind":"tts","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"char","unit_price":0.000007,"highlights":[]},{"id":"inworld-ai/realtime-tts-1.5-max","author":"inworld-ai","name":"Realtime TTS 1.5 Max","provider":"deepinfra","status":"live","blocked_by":null,"kind":"tts","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"char","unit_price":0.00005,"highlights":[]},{"id":"audio8/audio8-tts-preview-0.6b","author":"audio8","name":"Audio8 TTS Preview 0.6B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"tts","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"char","unit_price":0.000005,"highlights":[]},{"id":"bosonai/higgsaudiov2.5","author":"bosonai","name":"Higgsaudiov2.5","provider":"deepinfra","status":"live","blocked_by":null,"kind":"tts","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"char","unit_price":0.00002,"highlights":[]},{"id":"qwen/qwen3-tts","author":"qwen","name":"Qwen3 TTS","provider":"deepinfra","status":"live","blocked_by":null,"kind":"tts","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"char","unit_price":0.00002,"highlights":[]},{"id":"inworld-ai/realtime-tts-1.5-mini","author":"inworld-ai","name":"Realtime TTS 1.5 Mini","provider":"deepinfra","status":"live","blocked_by":null,"kind":"tts","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"char","unit_price":0.000025,"highlights":[]},{"id":"resembleai/chatterbox","author":"resembleai","name":"Chatterbox","provider":"deepinfra","status":"live","blocked_by":null,"kind":"tts","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"char","unit_price":0.00001,"highlights":[]},{"id":"zyphra/zonos-v0.1-hybrid","author":"zyphra","name":"Zonos V0.1 Hybrid","provider":"deepinfra","status":"live","blocked_by":null,"kind":"tts","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"char","unit_price":0.000007,"highlights":[]},{"id":"zyphra/zonos-v0.1-transformer","author":"zyphra","name":"Zonos V0.1 Transformer","provider":"deepinfra","status":"live","blocked_by":null,"kind":"tts","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"char","unit_price":0.000007,"highlights":[]},{"id":"qwen/qwen3-tts-voicedesign","author":"qwen","name":"Qwen3 TTS Voicedesign","provider":"deepinfra","status":"live","blocked_by":null,"kind":"tts","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"char","unit_price":0.00002,"highlights":[]},{"id":"inworld-ai/inworld-tts-1.5-mini","author":"inworld-ai","name":"Inworld TTS 1.5 Mini","provider":"deepinfra","status":"live","blocked_by":null,"kind":"tts","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"char","unit_price":0.000025,"highlights":[]},{"id":"inworld-ai/inworld-tts-1.5-max","author":"inworld-ai","name":"Inworld TTS 1.5 Max","provider":"deepinfra","status":"live","blocked_by":null,"kind":"tts","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"char","unit_price":0.00005,"highlights":[]},{"id":"resembleai/chatterbox-turbo","author":"resembleai","name":"Chatterbox Turbo","provider":"deepinfra","status":"live","blocked_by":null,"kind":"tts","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"char","unit_price":0.000001,"highlights":[]},{"id":"sesame/csm-1b","author":"sesame","name":"Csm 1B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"tts","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"char","unit_price":0.000007,"highlights":[]},{"id":"inworld-ai/realtime-tts-2","author":"inworld-ai","name":"Realtime TTS 2","provider":"deepinfra","status":"live","blocked_by":null,"kind":"tts","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"char","unit_price":0.000035,"highlights":[]},{"id":"openai/whisper-base.en","author":"openai","name":"Whisper Base.en","provider":"deepinfra","status":"live","blocked_by":null,"kind":"stt","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"minute","unit_price":0.03,"highlights":[]},{"id":"openai/whisper-timestamped-medium.en","author":"openai","name":"Whisper Timestamped Medium.en","provider":"deepinfra","status":"live","blocked_by":null,"kind":"stt","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"minute","unit_price":0.03,"highlights":[]},{"id":"openai/whisper-large-v3-turbo","author":"openai","name":"Whisper Large v3 Turbo","provider":"deepinfra","status":"live","blocked_by":null,"kind":"stt","edit":false,"free_kind":null,"context":448,"input_per_m":null,"output_per_m":null,"unit":"minute","unit_price":0.0002,"created":1727740800,"variant":"standard","reasoning":false,"input_modalities":["audio"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":true},"max_output":448,"description":"Speech transcription model for accurate audio-to-text and captioning workflows","highlights":[]},{"id":"openai/whisper-small.en","author":"openai","name":"Whisper Small.en","provider":"deepinfra","status":"live","blocked_by":null,"kind":"stt","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"minute","unit_price":0.03,"highlights":[]},{"id":"mistralai/voxtral-small-24b-2507","author":"mistralai","name":"Voxtral Small 24B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"stt","edit":false,"free_kind":null,"context":32000,"input_per_m":null,"output_per_m":null,"unit":"minute","unit_price":0.003,"created":1740787200,"variant":"standard","reasoning":false,"input_modalities":["audio","text"],"output_modalities":["text"],"capabilities":{"tools":false,"json":false,"reasoning":false,"vision":false,"audio":true},"max_output":32000,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","highlights":[]},{"id":"mistralai/voxtral-mini-3b-2507","author":"mistralai","name":"Voxtral Mini 3B 2507","provider":"deepinfra","status":"live","blocked_by":null,"kind":"stt","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"minute","unit_price":0.001,"highlights":[]},{"id":"qwen/qwen3-asr-0.6b","author":"qwen","name":"Qwen3 ASR 0.6B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"stt","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"minute","unit_price":0.0002,"highlights":[]},{"id":"qwen/qwen3-asr-1.7b","author":"qwen","name":"Qwen3 ASR 1.7B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"stt","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"minute","unit_price":0.00045,"highlights":[]},{"id":"openai/whisper-medium.en","author":"openai","name":"Whisper Medium.en","provider":"deepinfra","status":"live","blocked_by":null,"kind":"stt","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"minute","unit_price":0.03,"highlights":[]},{"id":"openai/whisper-tiny.en","author":"openai","name":"Whisper Tiny.en","provider":"deepinfra","status":"live","blocked_by":null,"kind":"stt","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"minute","unit_price":0.03,"highlights":[]},{"id":"openai/whisper-base","author":"openai","name":"Whisper Base","provider":"deepinfra","status":"live","blocked_by":null,"kind":"stt","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"minute","unit_price":0.03,"highlights":[]},{"id":"openai/whisper-timestamped-medium","author":"openai","name":"Whisper Timestamped Medium","provider":"deepinfra","status":"live","blocked_by":null,"kind":"stt","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"minute","unit_price":0.03,"highlights":[]},{"id":"nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b","author":"nvidia","name":"Nemotron 3.5 ASR Streaming Multilingual 0.6B","provider":"deepinfra","status":"live","blocked_by":null,"kind":"stt","edit":false,"free_kind":null,"context":null,"input_per_m":null,"output_per_m":null,"unit":"minute","unit_price":0.0002,"highlights":[]}],"usd_inr":{"rate":98.86,"spot":95.06,"marginPct":4,"markupInr":3.8,"markup":{"enabled":true,"mode":"percent","percentPct":4,"flatInr":1},"source":"frankfurter","ageHours":23.5,"stale":false}}