Nemotron 3 Ultra 550B A55B

LLM
NVIDIA

Nemotron 3 Ultra 550B A55B is a 550B-parameter sparse MoE model by NVIDIA built for complex reasoning, instruction following, and agentic tasks, with a 512K context window, tool use, thinking, and structured output support.

Context tokens

512,300

Output tokens

8,192

Training cutoff

May 1, 2026

Released

Jun 4, 2026

Schema

Reasoning mode is configurable — thinking can be enabled or disabled for each request.

Schema documentation

Capabilities

Tool use
Structured output
Thinking
Multilingual

Supported languages

de
en
es
fr
hi
it
ja
ko
pt
zh

Supported tools

  • Seclai Content Tools

    Inspect source documents connected to your account. Includes tools for loading full content, reading character ranges, searching within documents, viewing stats, and listing available content sources. When a source_connection_content_version_id is provided in agent run metadata it is used as the default. Otherwise the model can discover content via list_content_sources.

  • Seclai Knowledge Base

    Search your knowledge bases using semantic similarity. Includes search_knowledge_base and list_knowledge_bases. When a knowledge_base_id is provided in the prompt or agent run metadata it is used as the default. Otherwise the model can discover available knowledge bases at runtime.

  • Seclai Memory Banks

    Manage persistent memory across agent runs. Includes tools for listing memory banks, writing entries, searching memory via semantic similarity, and loading entries in chronological order. Supports two memory types: 'conversation' (speaker-attributed turns) and 'general' (freeform text). Use key to organize entries by topic, session, or user.

  • Seclai Web Tools

    Fetch web pages and search the web from within agent prompt calls. Includes seclai_web_fetch for retrieving page content in markdown, HTML, or plain text, and seclai_web_search for finding relevant pages with content snippets.

Pricing

TypeCreditsUnits
Input7.98Credits per 1k tokens
Output47.88Credits per 1k tokens
Cache hit2.66Credits per 1k tokens

Variants

No variants available for this model.

Try This Model

Write a prompt and experiment with Nemotron 3 Ultra 550B A55B in the model experiments page. You can compare it with other models side by side.