nvidia-nemotron-3-super-120b-a12b
nvidia/
NVIDIA model · Served by DeepInfra · live on the gateway
Pricing
About 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
What it supports
- Tool calling (function calling)
- JSON mode and structured output
- Image input (vision)
- Audio input
- Extended reasoning
- Streaming responses
- OpenAI SDK, Anthropic SDK and any OpenAI-compatible client
Make a request
curl https://rapidrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $RAPIDROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "nvidia/nvidia-nemotron-3-super-120b-a12b",
"messages": [{ "role": "user", "content": "Hello" }]
}'Frequently asked
How do I call nvidia-nemotron-3-super-120b-a12b through an OpenAI-compatible API?
Point any OpenAI-compatible client at https://rapidrouter.ai/api/v1 with a Rapid Router API key and set the model to nvidia/nvidia-nemotron-3-super-120b-a12b. The chat completions endpoint is https://rapidrouter.ai/api/v1/chat/completions.
What is the context window of nvidia-nemotron-3-super-120b-a12b?
nvidia-nemotron-3-super-120b-a12b has a context window of 262,144 tokens on Rapid Router, and returns up to 262,144 output tokens per reply.
What can nvidia-nemotron-3-super-120b-a12b do?
On Rapid Router, nvidia-nemotron-3-super-120b-a12b supports tool calling, JSON mode, extended reasoning.