nvidia

NVIDIA: Nemotron 3 Ultra (free)

by nvidia

OpenRouter
Tools Reasoning Long Context

Availability

Available 85 of 85 tracked days. Daily snapshots show whether this model was accessible as a free model on OpenRouter.

JulAug
ModelDays293031123456789101112131415161718192021222324252627
NVIDIA: Nemotron 3 Ultra (free)30

About

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...

Specifications

Context Length 1.0M
Max Output Tokens 66K
Modality text->text
Input text
Output text
Supported Parameters include_reasoning, max_tokens, reasoning, reasoning_effort, seed, temperature, tool_choice, tools, top_p
Content Moderation No

Error Rate

Based on feedback reported by Free LLM Router users. Error rate reflects the percentage of requests that encountered issues such as rate limiting, unavailability, or errors. Learn more.

Loading chart...
Model 1h 6h 24h 7d 30d
NVIDIA: Nemotron 3 Ultra (free) - - - 99.3% 99.3%

Similar Models

baidu Baidu Qianfan: CoBuddy (free) 131K z-ai Z.ai: GLM 5.1 203K arcee-ai Arcee AI: Trinity Large Thinking (free) 262K deepseek DeepSeek: DeepSeek V4 Flash (free) 1.0M google Google: Gemma 4 26B A4B (free) 262K

More from Nvidia

nvidia NVIDIA: Nemotron Nano 12B 2 VL (free) 128K nvidia NVIDIA: Nemotron 3 Super (free) 262K nvidia NVIDIA: Nemotron 3.5 Content Safety (free) 128K nvidia NVIDIA: Nemotron 3 Nano 30B A3B (free) 256K nvidia NVIDIA: Nemotron Nano 9B V2 (free) 128K

Frequently Asked Questions

Is NVIDIA: Nemotron 3 Ultra (free) free to use?

Yes, NVIDIA: Nemotron 3 Ultra (free) is completely free to use through OpenRouter. You can access it via the Free LLM Router API at no cost.

What is the context window for NVIDIA: Nemotron 3 Ultra (free)?

NVIDIA: Nemotron 3 Ultra (free) supports a context window of 1.0M tokens (1,000,000 tokens).

What is the maximum output length for NVIDIA: Nemotron 3 Ultra (free)?

NVIDIA: Nemotron 3 Ultra (free) can generate up to 66K tokens (65,536 tokens) per response.

Does NVIDIA: Nemotron 3 Ultra (free) support function calling (tools)?

Yes, NVIDIA: Nemotron 3 Ultra (free) supports function calling / tool use, enabling it to interact with external APIs and services.

Does NVIDIA: Nemotron 3 Ultra (free) support reasoning?

Yes, NVIDIA: Nemotron 3 Ultra (free) supports reasoning capabilities, allowing it to show its step-by-step thought process.