Nemotron 3 Ultra 550B API

Model details

Context window

262K tokens

Max output

—

Input

Text, images

Output

Text

Capabilities

Reasoning, Vision, Tool calling, Streaming, JSON output

Interfaces

OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses

Why teams pick it

• Nemotron 3 Ultra 550B for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.

Call Nemotron 3 Ultra 550B

Nemotron 3 Ultra 550B answers on any of the APIs below — pick the one your code already speaks and just swap in your Inferray key.

curl https://api.inferray.com/v1/chat/completions \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "nemotron-3-ultra-550b",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}'

curl https://api.inferray.com/v1/messages \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "nemotron-3-ultra-550b",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}'

curl https://api.inferray.com/v1/responses \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "nemotron-3-ultra-550b",
  "input": "Hello"
}'

Use Nemotron 3 Ultra 550B in your tools

Every coding agent below has a setup guide. Set the model to nemotron-3-ultra-550b.

• Claude Code
• Codex
• opencode
• Cline
• Roo Code
• Aider
• Continue

Alternatives to Nemotron 3 Ultra 550B

• GLM-4.5VGLM-4.5V for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.Z.ai
• Qwen3 VL 235B A22B InstructQwen3 VL 235B A22B Instruct for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.Alibaba
• DeepSeek V4 ProDeepSeek V4 Pro for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.DeepSeek

Questions about this model

How much does the Nemotron 3 Ultra 550B API cost?

Nemotron 3 Ultra 550B costs $0.5 per 1M input tokens and $2.2 per 1M output tokens on Inferray, and cached input is $0.1 per 1M. That is the list price, with no gateway fee on top.

Is there a free tier for Nemotron 3 Ultra 550B?

No. You add credit and pay Nemotron 3 Ultra 550B's list rate for each request — seats, projects, and API keys are free, and pay-as-you-go credit never expires.

Am I charged for failed requests?

No. A request that fails without returning a result is not billed. If a response fails part-way, the tokens already processed before the failure are charged.

Is Nemotron 3 Ultra 550B included in Token Plans?

No. Nemotron 3 Ultra 550B is pay-as-you-go only; Token Plans cover the other text models in the catalog.

Can I use Nemotron 3 Ultra 550B in Claude Code?

Yes. Set ANTHROPIC_BASE_URL to https://api.inferray.com, ANTHROPIC_AUTH_TOKEN to your Inferray key, and ANTHROPIC_MODEL to nemotron-3-ultra-550b. The same key works in Codex, opencode, Cline, and other agents.

Does Nemotron 3 Ultra 550B support tool calling and vision?

Nemotron 3 Ultra 550B supports tool calling, image input, reasoning, JSON output and streaming on Inferray.

Is it the real Nemotron 3 Ultra 550B?

Yes. A request for nemotron-3-ultra-550b is answered by Nemotron 3 Ultra 550B from NVIDIA, billed at its published list price. Inferray never substitutes a different or smaller model.