> ## Documentation Index
> Fetch the complete documentation index at: https://docs.venice.ai/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> The Venice API is OpenAI-compatible: use any OpenAI SDK with the base URL `https://api.venice.ai/api/v1` and a Venice API key, or pay per request from a USDC wallet through x402 with no account.
> Read model IDs from `GET /models` or `GET /models/traits` at runtime instead of hardcoding them from memory or from these pages. Models are added and retired often.
> Every model's price is in https://docs.venice.ai/pricing.md. Quote video and audio jobs with `POST /video/quote` or `POST /audio/quote` before you queue them.
> Search these docs from an MCP client at https://docs.venice.ai/mcp. The full agent guide is https://docs.venice.ai/agents.md.

# NVIDIA Nemotron 3 Ultra API

> NVIDIA Nemotron 3 Ultra API on Venice: 256K context, $0.625 input and $3.13 output per 1M tokens. Private, with zero data retention.



## NVIDIA Nemotron 3 Ultra API

NVIDIA Nemotron 3 Ultra is a large language model by NVIDIA, available on the Venice API as `nvidia-nemotron-3-ultra-550b-a55b`. This model is private and no prompt data is stored in any capacity.

NVIDIA Nemotron 3 Ultra is built for frontier reasoning, orchestration, coding agents, deep research, and complex enterprise workflows. It delivers up to 5x faster inference and up to 30% lower cost for agentic workloads.

### NVIDIA Nemotron 3 Ultra API pricing

| Model ID | Variant | Privacy | Price |
| - | - | - | - |
| `nvidia-nemotron-3-ultra-550b-a55b` | Standard | Private | $0.625 / $3.13 per 1M |

### NVIDIA Nemotron 3 Ultra specifications

| Spec | Value |
| - | - |
| Provider | NVIDIA |
| Released | Jun 4, 2026 |
| Privacy | Private |
| Status | Stable |
| Open weights | [nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B](https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B) |
| Context window | 256K tokens |
| Max output | 32K tokens |
| Reasoning effort | none, low, medium, high |
| Served precision | FP8 |
| [GPQA Diamond](https://docs.venice.ai/models/methodology.md#benchmarks) | 79.8% ±5.6 (95% interval), run by Venice through the API at its default reasoning on Nov 19, 2026 |

### How to use the NVIDIA Nemotron 3 Ultra API

Send requests to `POST https://api.venice.ai/api/v1/chat/completions` with `"model": "nvidia-nemotron-3-ultra-550b-a55b"` and your API key.

```bash theme={"system"}
curl https://api.venice.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia-nemotron-3-ultra-550b-a55b",
    "messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }],
    "reasoning_effort": "low"
  }'
```

### Related models

* [Grok Build 0.1 API](https://docs.venice.ai/models/grok-build-0-1.md): $1.00 / $2.00 per 1M
* [Seed 2.1 Turbo API](https://docs.venice.ai/models/seed-2-1-turbo.md): $0.625 / $3.13 per 1M
* [Qwen 3.8 27B E2EE API](https://docs.venice.ai/models/qwen-3-8-27b-e2ee.md): $0.47 / $3.53 per 1M
* [Kimi K2.7 Code API](https://docs.venice.ai/models/kimi-k2-7-code.md): $0.75 / $3.50 per 1M


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.