NVIDIA: Nemotron 3 Ultra (batch)
NVIDIA: Nemotron 3 Ultra (batch) offers a 512,288-token context window at $0.30 per 1M input tokens and $1.80 per 1M output tokens. Supported inputs: text. Data via OpenRouter /models, as of 2026-08-11.
Source: OpenRouter /models · as of 2026-08-11
Specifications
| Context window | 512,288 tokens |
|---|---|
| Input price | $0.30 / 1M tokens |
| Output price | $1.80 / 1M tokens |
| Input modalities | text |
| Output modalities | text |
| Model id | nvidia/nemotron-3-ultra-550b-a55b:batch |
Frequently asked questions
What is the context window of NVIDIA: Nemotron 3 Ultra (batch)?
NVIDIA: Nemotron 3 Ultra (batch) supports up to 512,288 tokens of context.
How much does NVIDIA: Nemotron 3 Ultra (batch) cost?
$0.30 per 1M input tokens and $1.80 per 1M output tokens (via OpenRouter /models, as of 2026-08-11).
What input types does NVIDIA: Nemotron 3 Ultra (batch) support?
NVIDIA: Nemotron 3 Ultra (batch) accepts text.
Related models
- Anthropic: Claude Fable Latest
- Anthropic Claude Haiku Latest
- Anthropic: Claude Opus Latest
- Anthropic Claude Sonnet Latest
- DeepSeek V4 Flash Latest
- Google Gemini Flash Latest
Build an optimized prompt for NVIDIA: Nemotron 3 Ultra (batch) with Prompeteer →