Skip to content
Not available in this workspace
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Pricing
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Support
  • Works With OR
  • Data

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube

For the free endpoint, please do not upload any confidential information or personal data (such as voices or faces of people). Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about NVIDIA's data processing practices, see Privacy Policy(opens in new tab). By using this free endpoint, you consent to NVIDIA's collection, recording, and use of such information and the NVIDIA API Trial Terms of Service(opens in new tab)

Favicon for nvidia

NVIDIA: Nemotron 3 Ultra

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

Model weights
Compare

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it supports text input and output with a context window of up to 1M tokens. It is suited for long-running agentic workflows, including agent orchestration, coding agents, deep research, and complex enterprise tasks.

It is particularly strong at multi-step reasoning and planning, with high-throughput inference designed for high-volume agent pipelines. It is part of the NVIDIA Nemotron family of open models for agentic AI.

Modalities

In / Out Price

$0.50 / $2.20per 1M

Context

512K

Released

Jun 4, 2026

Compare
ProvidersPricingPerformanceUptimeBenchmarksAppsActivityFAQ

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick — Balanced (price + speed), Nitro (fastest), or Exacto (highest tool-calling accuracy).

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Benchmarks

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows where this model lands among all models on OpenRouter.

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Activity

Token volume and request traffic to this model over time.

Quick Start

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

About NVIDIA: Nemotron 3 Ultra

OpenRouter makes NVIDIA: Nemotron 3 Ultra available through a unified, OpenAI-compatible API using the model ID nvidia/nemotron-3-ultra-550b-a55b. Requests can be routed across 4 providers, including DeepInfra, Baseten, Together and Venice, with automatic failover when an endpoint is unavailable.

NVIDIA: Nemotron 3 Ultra accepts text and returns text. It has a 512,288-token context window and a maximum output of 16,384 tokens.

On OpenRouter, NVIDIA: Nemotron 3 Ultra costs $0.50/M input tokens and $2.20/M output tokens, with separate rates for Cache Read at $0.10/M tokens. Effective pricing can be lower when prompt caching applies. It was released on June 4, 2026.

More models from Nvidia

  • Nemotron 3.5 ASR Streaming Multilingual 0.6B
  • Nemotron 3.5 Lightning
  • Nemotron 3 Embed 1B (free)

Frequently asked questions

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it supports text input and output with a context window of up to 1M tokens.

Nemotron 3 Ultra costs $0.50/M input tokens and $2.20/M output tokens, with separate rates for Cache Read at $0.10/M tokens.

Nemotron 3 Ultra has a 512,288 token context window. It supports up to 16,384 completion tokens.

Yes. Nemotron 3 Ultra accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

Nemotron 3 Ultra is served by 4 providers on OpenRouter: DeepInfra, Baseten, Together and Venice. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

Nemotron 3 Ultra was released on June 4, 2026.

$0.60$2.40$0.120.65s70 tps
100.00%
$0.60$3.60$0.200.84s68 tps
98.58%
$0.50$2.20$0.101.23s68 tps
91.40%
$0.625$3.125$0.18751.04s22 tps
88.31%

Throughput

70tok/s

P50, best across providers

Latency

0.65s

P50, best provider

AutoExacto Benchmarks
GPQA DiamondTAU-Bench
Together
81.2%--
Baseten
85.7%72.0%
Venice
--76.0%
Uptime (3d)

100.00%

Availability (3d)

98.82%

Availability over the last 3 days

Last 72 hours
Availability 98.82%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
98.81%
Without Routing
90.67%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and customization options.

1.
Favicon for https://nousresearch.com
Hermes Agent
Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.
13.4Btokens
2.
Favicon for https://portkey.ai/
Portkey AI
Control panel for AI apps
4.82Btokens
3.
Favicon for https://docs.all-hands.dev/
OpenHands
AI coding agent that can run commands, browse the web, call APIs
3.66Btokens
4.
Favicon for https://pi.dev/
pi
There are many coding agents, but this one is yours.
2.18Btokens
5.
Favicon for https://openclaw.ai/
OpenClaw
OpenClaw is an open-source AI agent that connects to your messaging apps and takes real actions on your behalf, from running commands and browsing the web to managing files and sending emails.
2.07Btokens