Skip to content
Rapid Router

Models

Every model in this catalog is callable right now with one API key: chat, image, video, speech and translation.

BrowseRankingsCompare
Free tier, sponsored by Rapid Router

Every :free model is paid for by us, from a -a-day sponsorship pool that resets daily at 18:30 UTC. Models marked always-free cost nothing to run and never pause.

of used today · free requests
Prices in624 models
Gemini 3.6 FlashFastestVisionReasoningTools

Fast Gemini model balancing multimodal reasoning, tool use, and cost

Google2mo ago1M context$0.750/M in$3.75/M out1.1s median99.9% success1.2K requests here
Ministral 14BVision

Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads

Mistral10mo ago262K context$0.200/M in$0.200/M out2.3s median100% success295 requests here
Llama-3.3-70B-InstructTools

Open Llama instruction model for multilingual chat, reasoning, and coding

Meta1y ago128K context$0.230/M in$0.400/M out3.1s median99.6% success259 requests here
MythoMax 13B

Open-weight instruction model for adaptable chat and self-hosted production workloads

Gryphe3y ago4K context$0.400/M in$0.400/M out2.1s median100% success129 requests here
Qwen3 235B-A22B Instruct 2507Tools

Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use

Qwen1y ago262K context$0.090/M in$0.550/M out3.4s median100% success100 requests here
GPT-4o miniVision

Small omni GPT for cheap multimodal assistance and production-scale traffic

OpenAI2y ago128K context$0.150/M in$0.600/M out1.2s median97.1% success99 requests here
DeepSeek V4 Flash 0731ReasoningTools:free

Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding

DeepSeek2mo ago1M context$0.060/M in$0.180/M out1.5s median100% success51 requests here
Llama 3.3 70B Euryale

Open Llama instruction model for multilingual chat, reasoning, and coding

Sao10k2y ago20K context$0.850/M in$0.850/M out3.0s median
GPT OSS 120BReasoningTools:free

Open GPT reasoning model for self-hosted agents and controllable deployments

OpenAI1y ago128K context$0.037/M in$0.170/M out6.5s median
Claude Haiku 4.5 (latest)FastestVisionReasoningTools

Fast Claude lane for lightweight agents, office tasks, and responsive chat

Anthropic1y ago200K context$1.00/M in$5.00/M out855ms median
GLM-5.3ReasoningTools

Flagship GLM model for long-horizon coding, agents, and complex project delivery

Z.ai2mo ago1M context$0.079/M in$4.80/M out66.3s median
GLM-5ReasoningTools

General GLM flagship for coding, analysis, and tool-heavy engineering workflows

Z.ai8mo ago205K context$1.00/M in$3.20/M out23.4s median
Qwen3.7 Flash (free)FreeVisionReasoningTools

Lightweight multimodal Qwen model for high-throughput text, image, and video tasks

Qwen3mo ago1M contextFree/M inFree/M out1.5s median
FLUX.1-schnellImage

Image model for prompt-driven generation, editing, and visual design workflows

Black Forest Labs2y ago77 context$0.00 per image587ms median
Nemotron 3.5 ASR Streaming Multilingual 0.6BTranscription
NVIDIA1.4s median
Ministral 8B (latest)VisionTools

Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads

Mistral2y ago262K context$0.150/M in$0.150/M out3.6s median
Whisper 3 LargeTranscription

Open Whisper checkpoint for robust multilingual transcription and captioning

OpenAI2y ago448 context624ms median
FLUX.1 Kontext ProImage
Black Forest Labs$0.04 per image4.0s median
Seedream 4.0Image
Bytedance$0.03 per image8.3s median
Gemini 3.5 Flash LiteFastestVisionReasoningTools

Fast Gemini model balancing multimodal reasoning, tool use, and cost

Google2mo ago1M context$0.300/M in$2.50/M out822ms median
Kokoro 82MSpeech
Hexgrad$0.004 per 1K characters1.1s median
text-embedding-3-smallEmbeddings

Embedding model for semantic search, retrieval, clustering, and ranking pipelines

OpenAI2y ago8K context$0.020/M in501ms median
GPT 6.1 SolVisionReasoningTools

Near-Astra performance for complex coding, computer use, and professional work at a lower cost.

OpenAI17d ago1.1M context$2.00/M in$10.00/M out2.3s median
Claude Sonnet 5FastestVisionReasoningTools

Everyday Claude agent model for coding, planning, browsing, and general work

Anthropic3mo ago1M context$2.00/M in$10.00/M out1.1s median
Qwen3-VL PlusFastestVisionReasoningTools

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen1y ago262K context$0.600/M in$4.80/M out995ms median
DeepSeek V3.2Tools

DeepSeek chat model for instruction following, coding, and analysis

DeepSeek1y ago164K context$0.260/M in$0.380/M out6.2s median
Fastwan Qad FP8 1.3BVideo
Fastvideo$0.01 per video4.9s median
Claude Opus 5.5VisionReasoningTools

Claude model for long-running agentic coding and knowledge work

Anthropic24d ago1M context$4.00/M in$20.00/M out1.5s median
Gemini 3.7 FlashVisionReasoningTools

High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning

Google2mo ago1M context$0.375/M in$1.88/M out2.0s median
Gemini 4 ArgonVisionReasoningTools

Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents

Google3d ago1M context$4.00/M in$20.00/M out10.1s median
Gemma 4 31B (free)FreeVisionReasoningTools:free

Largest Gemma 4 instruction model for open, self-hosted chat and reasoning

Google6mo ago262K contextFree/M inFree/M out1.2s median
Gemini 3.1 Pro PreviewVisionReasoningTools

Reasoning-first Gemini preview for agentic coding and complex problem solving

Google7mo ago1M context$2.00/M in$12.00/M out2.4s median
Nano-Banana-ProVisionTools

Image model for prompt-driven generation, editing, and visual design workflows

Google11mo ago66K context$2.00/M in$12.00/M out5.1s median
GPT 5 MiniVisionReasoning

Small GPT-5 for responsive agents, coding help, and everyday automation

OpenAI1y ago400K context$0.250/M in$2.00/M out1.3s median
GPT 4.1 MiniVision

Affordable GPT-4.1 lane for fast coding help and structured extraction

OpenAI1y ago1M context$0.400/M in$1.60/M out1.1s median
Llama-3.3-70B-Instruct (free)FreeTools:free

Open Llama instruction model for multilingual chat, reasoning, and coding

Meta1y ago128K contextFree/M inFree/M out1.1s median
Llama 3.1 70B Euryale

Open Llama instruction model for multilingual chat, reasoning, and coding

Sao10k2y ago20K context$0.850/M in$0.850/M out2.4s median
Bulbul V3Speech
Sarvam$0.002 per 1K characters405ms median
MayuraTranslate
Sarvam$0.002 per 1K characters1.2s median
Gemini Flash LatestVisionReasoningTools

High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning

Google2mo ago1M context$0.375/M in$1.88/M out2.1s median
Claude Opus 5VisionReasoningTools

Strongest Claude Opus model for coding, agents, and professional work

Anthropic2mo ago1M context$5.00/M in$25.00/M out1.0s median
Qwen3.7 FlashVisionReasoningTools

Lightweight multimodal Qwen model for high-throughput text, image, and video tasks

Qwen3mo ago1M context$0.030/M in$0.130/M out388ms median
GPT 5.6 LunaLongest contextVisionReasoningTools

Cost-efficient GPT-5.6 model for fast, high-volume workloads

OpenAI3mo ago1.1M context$0.200/M in$1.20/M out858ms median
Grok 4.5VisionReasoningTools

xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk

xAI3mo ago500K context$2.00/M in$6.00/M out807ms median
Claude Fable 5VisionReasoningTools

Claude model for creative writing, analysis, and controlled agent workflows

Anthropic4mo ago1M context$10.00/M in$50.00/M out2.6s median
Claude Opus 4.8VisionReasoningTools

Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents

Anthropic4mo ago1M context$5.00/M in$25.00/M out799ms median
Gemini 3.5 FlashVisionReasoningTools

Fast Gemini model balancing multimodal reasoning, tool use, and cost

Google5mo ago1M context$1.50/M in$9.00/M out847ms median
Claude Opus 4.7VisionReasoningTools

Stronger Opus tier for advanced software work and high-stakes reasoning

Anthropic6mo ago1M context$5.00/M in$25.00/M out731ms median
Gemma 4 26B A4B ITVisionReasoningTools

Open Gemma instruction model for efficient chat and self-hosted deployments

Google6mo ago262K context$0.070/M in$0.340/M out900ms median
Claude Sonnet 4.6VisionReasoningTools

Claude workhorse for coding agents, careful analysis, and production cost control

Anthropic8mo ago1M context$3.00/M in$15.00/M out946ms median
Claude Opus 4.6VisionReasoningTools

High-end Claude for difficult coding, planning, and slower expert reasoning

Anthropic8mo ago1M context$5.00/M in$25.00/M out1.6s median
Gemini 3 Flash PreviewVisionReasoningTools

New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs

Google10mo ago1M context$0.500/M in$3.00/M out1.1s median
GLM-4.6VVisionReasoningTools

GLM vision model for visual reasoning, documents, and multimodal agents

Z.ai10mo ago128K context$0.300/M in$0.900/M out271ms median
Ministral 3 14BVisionTools

Open vision-language model for efficient local deployment, instruction following, and tool use

Mistral10mo ago262K context$0.200/M in$0.200/M out382ms median
Claude Opus 4.5 (latest)VisionReasoningTools

Flagship Claude model for deep reasoning, coding, and long-horizon agents

Anthropic10mo ago200K context$5.00/M in$25.00/M out1.3s median
Claude Sonnet 4.5 (latest)VisionReasoningTools

Balanced Claude model for coding, analysis, agent workflows, and cost control

Anthropic1y ago200K context$3.00/M in$15.00/M out886ms median
Sarvam 105BReasoningTools

Flagship Indian-language reasoning model for enterprise multilingual applications

Sarvam1y ago131K context$0.360/M in$0.900/M out231ms median
Nano BananaImageVisionReasoning

Nano Banana image model for fast generation, edits, and character-consistent assets

Google1y ago33K context$0.04 per image4.3s median
FLUX.1-Kontext-devImageVision

Image model for prompt-driven generation, editing, and visual design workflows

Black Forest Labs1y ago41K context$0.02 per image8.4s median
Wan2.2-T2V-A14BVideo

Video model for prompt-guided generation, editing, and motion workflows

Wan Ai1y ago100 context$0.38 per video271.5s median