# Nemotron 3 Ultra 550B A55B API pricing

No price from the maker itself is on record for Nemotron 3 Ultra 550B A55B. The lowest of 23 providers is routing.run: $0.1 per 1M input tokens and $0.1 per 1M output tokens (as of 2026-11-12). Context window: 1M tokens, up to 65.5K output tokens per request.

- Type: Text
- Context: 1M
- Max output: 65.5K
- Released: 2026-06-04
- Open weights: Yes

## Price by provider (USD per 1M tokens)

| Provider | Model id | Input | Output | Cached | Notes |
| --- | --- | --- | --- | --- | --- |
| [Nvidia](https://docs.api.nvidia.com/nim/) | nvidia/nemotron-3-ultra-550b-a55b | $0 | $0 | — | Official |
| [routing.run](https://docs.routing.run/api-reference/models) | nemotron-3-ultra | $0.1 | $0.1 | — | Lowest |
| [Kilo Gateway](https://kilo.ai) | nvidia/nemotron-3-ultra-550b-a55b | $0.4 | $1.76 | $0.08 |  |
| [DigitalOcean](https://docs.digitalocean.com/products/gradient-ai-platform/details/models/) | nemotron-3-ultra-550b | $0.9 | $1.7 | $0.18 |  |
| [CoreWeave](https://docs.wandb.ai/inference) | nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | $0.5 | $2.15 | $0.1 |  |
| [Eden AI](https://docs.edenai.co) | deepinfra/nemotron-3-ultra-550b-a55b | $0.5 | $2.2 | $0.1 |  |
| [DevPass (LLM Gateway)](https://llmgateway.io/docs) | nemotron-3-ultra-550b | $0.5 | $2.2 | $0.1 |  |
| [Baseten](https://docs.baseten.co/inference/model-apis/overview) | nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | $0.6 | $2.4 | $0.12 |  |
| [CommandCode](https://commandcode.ai/docs/provider) | nvidia/nemotron-3-ultra-550b-a55b | $0.6 | $2.4 | $0.12 |  |
| [NanoGPT](https://docs.nano-gpt.com) | nvidia/nemotron-3-ultra-550b-a55b | $0.5 | $2.5 | $0.15 |  |
| [NanoGPT](https://docs.nano-gpt.com) | nvidia/nemotron-3-ultra-550b-a55b:thinking | $0.5 | $2.5 | $0.15 |  |
| [OpenRouter](https://openrouter.ai/models) | nvidia/nemotron-3-ultra-550b-a55b | $0.6 | $2.4 | $0.12 |  |
| [Requesty](https://requesty.ai/solution/llm-routing/models) | nvidia-nemotron-3-ultra | $0.5 | $2.5 | — |  |
| [Vercel AI Gateway](https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway) | nvidia/nemotron-3-ultra-550b-a55b | $0.6 | $2.4 | $0.12 |  |
| [Ollama Cloud](https://docs.ollama.com/cloud) | nemotron-3-ultra | $0.1 | $3 | $0.1 |  |
| [Venice AI](https://docs.venice.ai) | nvidia-nemotron-3-ultra-550b-a55b | $0.625 | $3.125 | $0.1875 |  |
| [Eden AI](https://docs.edenai.co) | nebius/nvidia/Nemotron-3-Ultra-550b-a55b | $1 | $3 | $1 |  |
| [Nebius Token Factory](https://docs.tokenfactory.nebius.com/) | nvidia/Nemotron-3-Ultra-550b-a55b | $1 | $3 | $0.12 |  |
| [Eden AI](https://docs.edenai.co) | arkanecloud/nvidia/nemotron-3-ultra-550b-a55b | $0.6 | $3.5 | $0.2 |  |
| [Kenari](https://kenari.id/docs) | nemotron-3-ultra-550b-a55b | $0.685714 | $4.285714 | $0.068571 |  |
| [Thinking Machines](https://tinker-docs.thinkingmachines.ai/tinker/compatible-apis/anthropic/) | nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 | $1.8 | $6.225 | $0.36 |  |
| [Thinking Machines](https://tinker-docs.thinkingmachines.ai/tinker/compatible-apis/anthropic/) | nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16:peft:262144 | $1.8 | $6.225 | $0.36 |  |
| [Together AI](https://docs.together.ai/docs/serverless-models) | nvidia/nemotron-3-ultra-550b-a55b | $0.6 | $3.6 | $0.2 | Deprecated |
| [AIHubMix](https://docs.aihubmix.com) | nemotron-3-ultra-550b-a55b-free | $0 | $0 | — |  |
| [Bothub](https://bothub.ru/models) | nemotron-3-ultra-550b-a55b:free | $0 | $0 | — |  |
| [Kilo Gateway](https://kilo.ai) | nvidia/nemotron-3-ultra-550b-a55b:free | $0 | $0 | — |  |
| [OpenCode](https://opencode.ai/v2/docs/console/models/) | nemotron-3-ultra-free | $0 | $0 | $0 | Deprecated |
| [OpenRouter](https://openrouter.ai/models) | nvidia/nemotron-3-ultra-550b-a55b:free | $0 | $0 | — |  |
| [Requesty](https://requesty.ai/solution/llm-routing/models) | nemotron-3-ultra-550b-a55b | $0 | $0 | — |  |
| [UnoRouter](https://unorouter.com/models) | nemotron-3-ultra-550b-a55b:free | $0 | $0 | — |  |

Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.

Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.

https://apibook.ai/models/nvidia/nemotron-3-ultra-550b-a55b/