Every NVIDIA model below is callable right now through Rapid Router with one API key. The price next to each model is the provider's list price per million tokens; it is exactly what your balance is debited. Our platform fee is charged once, when you buy credits, so there is nothing added per request.
To use a NVIDIA model, point the OpenAI SDK (or any OpenAI-compatible client) at https://rapidrouter.ai/api/v1, set the model string to the id shown in grey, and send the same request you send today.
Llama 3.1 Nemotron 70B InstructToolsnvidia/llama-3.1-nemotron-70b-instruct
Nemotron model for efficient reasoning, coding, and specialized AI agents
128K context$1.20/M in$1.20/M out464ms100% ok1y ago
Llama 3.3 Nemotron Super 49B v1.5ReasoningToolsnvidia/llama-3.3-nemotron-super-49b-v1.5
Nemotron model for efficient reasoning, coding, and specialized AI agents
131K context$0.400/M in$0.400/M out509ms100% ok1y ago
llama-nemotron-embed-vl-1b-v2Visionnvidia/llama-nemotron-embed-vl-1b-v2
Embedding model for semantic search, retrieval, clustering, and ranking pipelines
33K context$0.010/M in682ms100% ok8mo ago
Nemotron 3 Embed 1B Bf16nvidia/nemotron-3-embed-1b-bf16
$0.015/M in849ms100% ok
Nemotron 3 Embed 1B Nvfp4nvidia/nemotron-3-embed-1b-nvfp4
$0.010/M in436ms100% ok
Nemotron 3 Embed 8Bnvidia/nemotron-3-embed-8b
$0.035/M in2.2s100% ok
Nemotron 3 Nano 30B A3BReasoningToolsnvidia/nemotron-3-nano-30b-a3b
Small Nemotron 3 MoE for efficient coding, math, and long-context agents
262K context$0.050/M in$0.200/M out432ms100% ok10mo ago
Nemotron 3 Nano Omni 30B A3B ReasoningVisionReasoningToolsnvidia/nemotron-3-nano-omni-30b-a3b-reasoning
Open Nemotron omni model combining reasoning with text, vision, and audio
262K context$0.200/M in$0.800/M out498ms100% ok5mo ago
Nemotron 3 Ultra 550B A55BReasoningToolsnvidia/nemotron-3-ultra-550b-a55b
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...
203K context$0.600/M in$3.60/M out585ms100% ok4mo ago
Nemotron 4 340B Instructnvidia/nemotron-4-340b-instruct
$4.20/M in$4.20/M out423ms100% ok
Nemotron Content Safety 3.5nvidia/nemotron-content-safety-3.5
$0.200/M in$0.200/M out325ms100% ok
nvidia-nemotron-3-super-120b-a12bReasoningToolsnvidia/nvidia-nemotron-3-super-120b-a12b
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
262K context$0.085/M in$0.400/M out653ms100% ok7mo ago
nvidia-nemotron-3-super-120b-a12b (free)FreeReasoningToolsnvidia/nvidia-nemotron-3-super-120b-a12b:free
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
262K context$0.085/M in$0.400/M out1.0s100% ok7mo ago
Nemotron 3 UltraReasoningToolsnvidia/nvidia-nemotron-3-ultra-550b-a55b
Nemotron 3 Ultra is a powerful MoE model designed for long-running agents across coding, deep research, and enterprise automation.
262K context$0.500/M in$2.20/M out424ms100% ok4mo ago
Nemotron 3 Ultra 550B A55BReasoningToolsnvidia/nvidia-nemotron-3-ultra-550b-a55b-bf16
Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy
1M context$1.00/M in$5.00/M out427ms100% ok4mo ago
Nvidia Nemotron 3.5 Lightningnvidia/nvidia-nemotron-3.5-lightning
$0.060/M in$0.160/M out467ms100% ok
Nvidia Nemotron Nano 12B V2 VLnvidia/nvidia-nemotron-nano-12b-v2-vl
$0.200/M in$0.600/M out1.2s100% ok
nvidia-nemotron-nano-9b-v2ReasoningToolsnvidia/nvidia-nemotron-nano-9b-v2
Compact Nemotron model for efficient reasoning and deployable AI agents
131K context$0.040/M in$0.160/M out507ms100% ok1y ago
Parakeet Tdt 0.6Bnvidia/parakeet-tdt-0.6b
534ms100% ok
Nemotron 3.5 ASR Streaming Multilingual 0.6Bnvidia/nemotron-3.5-asr-streaming-multilingual-0.6b
1.4s85.7% ok