NVIDIA: Nemotron 3 Ultra (free)
by Kilo Gateway · family nemotron · listed Jun 2026RTW
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... **Terms of service** For NVIDIA free endpoints (Super/Ultra/etc): Trial use only - do not submit personal or confidential data. 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 our data processing practices, see our [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).
Current rates USD per 1M tokens
Against the market
On the record
- Model id
nvidia/nemotron-3-ultra-550b-a55b:free- Context window
- 1M tokens
- Max output
- 66K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2026-06-04
- Last updated
- 2026-06-04
- Provider docs
- kilo.ai
Back of the envelope
≈
Also listed at
- OpenRouterfree in · free out
- UnoRouterfree in · free out