Nemotron 3 Ultra (free)
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.
nvidia/nemotron-3-ultra-550b-a55b:free
- Context
- 1M tokens
- Completion cap
- 65,536
- Tools
- Yes
- JSON
- No
- Released
- 2026-06-04
Call it from Geek Hub
Same OpenAI SDK. Change the base URL and the model id.
curl https://api.geekhub.mx/v1/chat/completions \
-H "Authorization: Bearer $GEEKHUB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "nvidia/nemotron-3-ultra-550b-a55b:free",
"messages": [{"role": "user", "content": "Hola"}]
}'Frequently asked questions
- What is Nemotron 3 Ultra (free)?
- 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. Nemotron 3 Ultra (free) runs on the Geek Hub API (OpenAI-compatible). Model id: nvidia/nemotron-3-ultra-550b-a55b:free.
- Is Nemotron 3 Ultra (free) free?
- Yes. The listed price is zero — you are not charged for prompt or completion tokens. Free endpoints are rate limited.
- What is the context length of Nemotron 3 Ultra (free)?
- Nemotron 3 Ultra (free) has a 1M tokens context window. It supports up to 65,536 completion tokens.
- Does Nemotron 3 Ultra (free) support tool calling and structured outputs?
- Nemotron 3 Ultra (free) accepts tools and tool_choice for function calling. Structured outputs are not listed for this endpoint.
- When was Nemotron 3 Ultra (free) released?
- Nemotron 3 Ultra (free) was released on 2026-06-04.
More models from NVIDIA
- Nemotron 3 Nano 30B A3BNVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully
- Nemotron 3 Nano 30B A3B (free)NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully
- Nemotron 3 Nano Omni (free)NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, vide
- Nemotron 3 SuperNVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. B
- Nemotron 3 Super (free)NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. B
- Nemotron 3 UltraNVIDIA 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 m