Nemotron 3 Ultra
| Provider | Price | Provider model ID | Status | Context / max output | Source |
|---|---|---|---|---|---|
 OpenRouterFree variant | Router catalog Tariff not listedInput $0USD / 1M tokensOutput $0USD / 1M tokens OpenRouter · Router catalogInput: $0 Output: $0 OpenRouter route catalog price, not a direct-provider price. Routing, modality and endpoint conditions can change the actual bill. Checked 2026-10-03T12:45:17.276Z Price source ↗ | nvidia/nemotron-3-ultra-550b-a55b:free | Catalog-listedConditionsCheck regional and account eligibility in provider documentation. | Context tokens 1000000Output tokens 65536 | Official source ↗2026-09-28 |
 DeepInfra | Standard list Tariff not listedInput $0.5USD / 1M tokensOutput $2.2USD / 1M tokens DeepInfra · Standard listInput: $0.5 Output: $2.2 Published cents-per-token list rate. Account discounts and cache/service-tier modifiers are not applied. Checked 2026-10-03T12:45:17.276Z Price source ↗ | nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | Catalog-listedConditionsCatalog-listed; account access and regional availability may apply. | Context tokens 262144 | Official source ↗2026-09-28 |
| OpenRouter | Router catalog Tariff not listedInput $0.5USD / 1M tokensOutput $2.2USD / 1M tokens OpenRouter · Router catalogInput: $0.5 Output: $2.2 Cache Read: $0.1 OpenRouter route catalog price, not a direct-provider price. Routing, modality and endpoint conditions can change the actual bill. Checked 2026-10-03T12:45:17.276Z Price source ↗ | nvidia/nemotron-3-ultra-550b-a55b | Catalog-listedConditionsCatalog-listed; account access and regional availability may apply. | Context tokens 262144Output tokens 182520 | Official source ↗2026-09-28 |
Nemotron 3 Ultra accepts text and produces text. Tool calling and structured outputs are available on supported routes.
Specifications
- Catalog model ID
- nvidia/nemotron-3-ultra-550b-a55b
- Developer model ID / revision
- Not verified in cited sources
- Input modalities
- textOpenRouter catalog ↗
- Output modalities
- textOpenRouter catalog ↗
- Context / input token limit
- 1,048,576Developer model card ↗
- Maximum output tokens
- 182,520OpenRouter catalog ↗
- Tool calling
- SupportedOpenRouter catalog ↗
- Structured output
- SupportedOpenRouter catalog ↗
- API parameters (source-specific)
- frequency_penalty, include_reasoning, logit_bias, max_tokens, min_p, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_pOpenRouter catalog ↗
- API parameter scope
- OpenRouter API; support varies by route
- Weight access
- Open weightsDeveloper model card ↗
- Weight license / access terms
- OpenMDW 1.1Developer model card ↗
- Total parameters (billions)
- 550Developer model card ↗
- Active parameters (billions)
- 55Developer model card ↗
- Download size (GB)
- Depends on checkpoint and precision; no verified file size
- Release date
- 2026-06-04Developer model card ↗
- Added to OpenRouter
- 2026-06-04OpenRouter catalog ↗
- Notes
- API parameter names are reported by OpenRouter and do not describe the developer’s native API. Token limits labeled OpenRouter are route catalog limits, not universal model limits. Media limits on this page describe the linked provider endpoint; other deployments may differ. The model card supports up to 1M context; the OpenRouter route currently exposes 262,144 tokens. Check deployment settings before using the full model window.
Catalog entries link to their specification and availability sources. This is a curated selection, not every model each provider offers. Best prices are the lowest collected USD tariffs, not a total-cost estimate. Token offers are selected by input price, with output from the same tariff; workload mix may change the cheapest provider. Listed variants may require batch processing, off-peak hours, or specific media settings. Price coverage varies by provider; collected tariffs include their source and observation time. Benchmark scores are a dated snapshot, not a live feed or a universal measure of quality. They apply to the shown evaluation configuration; listed prices may use different settings. Models without verified scores are not assumed to be weaker.