Nemotron 3 Ultra
Nemotron 3 Ultra is NVIDIA's largest open reasoning model, a hybrid Mamba-Transformer MoE with 550B total and 55B active parameters, latent MoE routing, multi-token prediction, and a context window of 1M tokens for long-running agent workflows.
View API reference- Input and output price
- Prices from: Input $0.60, Output $2.40, Per 1M tokens
- 24h uptime
- Loading AI Gateway uptime
import { streamText } from 'ai'
const result = streamText({ model: 'nvidia/nemotron-3-ultra-550b-a55b', prompt: 'Why is the sky blue?'})Copy link to headingPlayground
Try out Nemotron 3 Ultra by NVIDIA. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
Nemotron 3 Ultra
Nemotron 3 Ultra
Copy link to headingProviders
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
Copy link to headingUptime24 hours
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
Copy link to headingThroughput24 hours
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
Copy link to headingLatency24 hours
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Getting started
Call Nemotron 3 Ultra through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.
Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'nvidia/nemotron-3-ultra-550b-a55b', prompt: 'Why is the sky blue?', });
console.log(result.text);}
main().catch(console.error);Top-level parameters
The same Nemotron 3 Ultra request in each API format AI Gateway supports.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'nvidia/nemotron-3-ultra-550b-a55b', system: 'You are a concise technical assistant.', prompt: 'Summarize the tradeoffs between static generation and SSR.', maxOutputTokens: 1024, });
console.log(result.text);}
main().catch(console.error);Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | Yes | Model ID in the form creator/model, e.g. nvidia/nemotron-3-ultra-550b-a55b. AI Gateway routes the request to an available provider. |
maxOutputTokens | number | No | Hard cap on generated tokens. Nemotron 3 Ultra supports up to 262,000 output tokens. Reasoning tokens count toward this limit. |
reasoning | 'provider-default' | 'none' | 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' | No | Provider-agnostic reasoning effort, available in AI SDK 7 or later. Maps to the provider’s native reasoning configuration; reasoning settings under providerOptions take precedence when both are set. See the Reasoning section below. |
providerOptions | Record<string, JSONValue> | No | AI Gateway routing options under gateway, plus any provider-native options under the provider’s own namespace — see the table below. |
Input limits
| Input | Formats | Sources | Max count | Max size | Limits |
|---|---|---|---|---|---|
| Text | — | — | — | — | Prompt and response share the 1M-token context window |
Provider options
Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.
Learn more in the AI SDK provider docs.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'nvidia/nemotron-3-ultra-550b-a55b', prompt: 'Why is the sky blue?', providerOptions: { gateway: { only: ['togetherai', 'deepinfra'], }, }, });
console.log(result.text);}
main().catch(console.error);These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.
| Parameter | Type | Required | Description |
|---|---|---|---|
providerOptions.gateway.only | string[] | No | Restrict routing to these provider slugs. Requests fail over only within the listed providers. |
providerOptions.gateway.order | string[] | No | Preferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks. |
providerOptions.gateway.sort | 'cost' | 'ttft' | 'tps' | No | Rank candidate providers by price, time to first token, or tokens per second instead of the default routing order. |
providerOptions.gateway.zeroDataRetention | boolean | No | Route only to providers with a zero-data-retention policy for this model. |
Routing across providers
AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.
Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.
Reasoning
AI Gateway bridges reasoning across every API format. The AI SDK exposes a provider-agnostic top-level reasoning level (none, minimal, low, medium, high, or xhigh); the Chat Completions and Responses formats take the same effort under reasoning.effort; and the Anthropic Messages format uses a native thinking token budget. Whichever you send, the gateway maps it to the target model’s native configuration, converting between effort levels and token budgets as needed. Reasoning-related settings under providerOptions take full precedence over the top-level reasoning value and are never merged. Reasoning tokens typically count toward your output-token usage, though how they’re reported and billed varies by provider.
Learn more in the AI Gateway reasoning guide.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'nvidia/nemotron-3-ultra-550b-a55b', prompt: 'Explain the Monty Hall problem step by step.', reasoning: 'high', });
console.log(result.text);}
main().catch(console.error);Tool calling
Expose tools the model can call. Define each tool’s inputs with a Zod schema.
import { generateText, tool } from 'ai';import { z } from 'zod';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'nvidia/nemotron-3-ultra-550b-a55b', prompt: 'What is the weather in San Francisco?', tools: { getWeather: tool({ description: 'Get the current weather for a location', inputSchema: z.object({ location: z.string() }), execute: async ({ location }) => ({ location, temperatureC: 18 }), }), }, });
console.log(result.text);}
main().catch(console.error);Copy link to headingMore models by NVIDIA
| Model |
|---|
| 262K | 0.2 s | 521 tps | $0.05/M | $0.15/M | Read$0.01/M | — |    | 08/11/2026 | ||||||
| 256K | 0.2 s | 130 tps | $0.15/M | $0.65/M | — |  | 03/11/2026 | |||||||
| 262K | 0.3 s | 128 tps | $0.05/M | $0.24/M | — | | 12/15/2025 | |||||||
| 131K | 0.1 s | 45 tps | $0.20/M | $0.60/M | — | | 10/28/2025 | |||||||
| 131K | 0.2 s | 149 tps | $0.06/M | $0.23/M | — | | 08/18/2025 |
Copy link to headingAbout Nemotron 3 Ultra
NVIDIA released Nemotron 3 Ultra on June 4, 2026 as the largest model in the Nemotron 3 family, completing the tier above Nano and Super. It carries 550B total parameters with 55B active per token, and NVIDIA positions it as the reasoning and orchestration layer for long-running agent workflows: the model that handles planning, synthesis, and verification while lighter models execute routine steps.
The architecture interleaves three layer types. Mamba layers process long sequences with linear-time complexity, which keeps a context window of 1M tokens practical. Transformer attention layers appear at select depths to preserve precise recall from large contexts. Latent mixture-of-experts (MoE) routing compresses token embeddings into a smaller latent space before selecting experts, so distinct specialists activate for reasoning, coding, and tool calls without dense compute. Multi-token prediction (MTP) layers predict several future tokens per forward pass, providing built-in speculative decoding for long outputs.
Nemotron 3 Ultra scores 91% on PinchBench, 82% on IFBench, and 95% on Ruler at 1M tokens. Weights, data, and recipes are released under the Linux Foundation's permissive OpenMDW-1.1 license. Full details: https://www.together.ai/models/nvidia-nemotron-3-ultra.
Copy link to headingWhat To Consider When Choosing a Provider
- Configuration: Long-running agent sessions accumulate tokens quickly, and a context window of 1M tokens makes it easy to carry everything forward. Budget for that before you scale. Compare $0.5 and $2.4, and use prompt caching at $0.12 for repeated prefixes like system prompts and tool definitions.
- Configuration: Output is capped at 262K tokens per request, so plan chunking for very long generations. Nemotron 3 Ultra is the flagship tier of the Nemotron 3 family. Reserve it for the planning and verification calls that need the depth, and route routine steps to smaller Nemotron 3 models.
- Zero Data Retention: Zero Data Retention is available for this model. It is offered on a per-provider and model basis. See the documentation for details.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
Copy link to headingWhen to Use Nemotron 3 Ultra
Best for
- Agent Orchestration Backbones: Planning, synthesis, and verification steps in long-running multi-agent pipelines
- Long-Horizon Coding Agents: Multi-step software tasks that span large codebases and extended tool-call sequences
- Deep Research Workflows: Gathering, cross-checking, and synthesizing evidence across many sources in one context
- Full-Context Session Handling: Keeping complete agent histories, codebases, or document sets in a single pass
- Open-Model Requirements: Teams that need open weights and permissive licensing for governance or reproducibility
Consider alternatives when
- Lightweight Task Execution: Nemotron 3 Nano handles routine pipeline steps at far lower compute
- Mid-Tier Agent Planning: Nemotron 3 Super covers complex multi-agent decisions at a smaller footprint
- Vision or Multimodal Inputs: Nemotron 3 Ultra is a text reasoning model, so image and video tasks need a vision-language model
- Cost-First Workloads: A smaller model may deliver acceptable quality at lower per-token rates
Copy link to headingConclusion
Nemotron 3 Ultra closes out the Nemotron 3 family as its reasoning and orchestration tier, pairing latent MoE efficiency with a context window of 1M tokens. Route it through AI Gateway with unified auth and billing, and call it with the AI SDK or through Chat Completions, Responses, Messages, and other API formats.
Copy link to headingFrequently Asked Questions
Why does "550B total, 55B active" matter for inference cost?
You pay compute proportional to the active parameters, not the total. Nemotron 3 Ultra draws on 550B parameters of learned knowledge while activating 55B per token. Latent MoE routing selects the relevant experts in a compressed latent space, which keeps routing overhead low.
How does Nemotron 3 Ultra fit alongside Nemotron 3 Nano and Super?
Nemotron 3 Ultra is the largest tier of the Nemotron 3 family. Nano (30B/3B active) handles high-throughput lightweight steps, Super (120B/12B active) covers mid-tier multi-agent planning, and Nemotron 3 Ultra takes the hardest planning, synthesis, and verification calls. Many pipelines pair a smaller tier for routine steps with Nemotron 3 Ultra for complex decisions.
How does Nemotron 3 Ultra handle a context window of 1M tokens?
Mamba layers process sequences with linear-time complexity, so long contexts avoid the quadratic memory growth of pure attention. Nemotron 3 Ultra scores 95% on the Ruler benchmark at 1M tokens, which tests recall across very long inputs.
Is Nemotron 3 Ultra open source?
Yes. NVIDIA released the weights, data, and recipes under the Linux Foundation's OpenMDW-1.1 license, a permissive license built for open model distributions.
Does Nemotron 3 Ultra support Zero Data Retention?
Yes, Zero Data Retention is available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.
Where are per-token prices listed?
Rates are listed on this page. They reflect the providers routing through AI Gateway and shift when providers update their pricing.