Skip to content
Rapid Router
← All models

Nemotron 3 Ultra

nvidia/nvidia-nemotron-3-ultra-550b-a55b

NVIDIA model · Served by DeepInfra · live on the gateway

Try in chatGet API key
Input / 1M
$0.500
Output / 1M
$2.20
Context
262K tokens
Max output
262K tokens
Input
Text
Released
4mo ago

Pricing

Input tokens$0.500 per 1M
Output tokens$2.20 per 1M
Provider list priceExactly what your balance is debited; our fee is charged when you buy credits

About Nemotron 3 Ultra

Nemotron 3 Ultra is a powerful MoE model designed for long-running agents across coding, deep research, and enterprise automation.

ReasoningTools

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-ultra-550b-a55b",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'

Frequently asked

How do I call Nemotron 3 Ultra 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-ultra-550b-a55b. The chat completions endpoint is https://rapidrouter.ai/api/v1/chat/completions.

What is the context window of Nemotron 3 Ultra?

Nemotron 3 Ultra has a context window of 262,144 tokens on Rapid Router, and returns up to 262,144 output tokens per reply.

What can Nemotron 3 Ultra do?

On Rapid Router, Nemotron 3 Ultra supports tool calling, JSON mode, extended reasoning.

More NVIDIA Nemotron models

Llama 3.1 Nemotron 70B Instruct$1.20/M in · $1.20/M outLlama 3.3 Nemotron Super 49B v1.5$0.400/M in · $0.400/M outNemotron 3 Nano 30B A3B$0.050/M in · $0.200/M outNemotron 3 Nano Omni 30B A3B Reasoning$0.200/M in · $0.800/M outNemotron 3 Ultra 550B A55B$0.600/M in · $3.60/M outNemotron 4 340B Instruct$4.20/M in · $4.20/M outEvery NVIDIA model, priced →