Model prices / NVIDIA / Nemotron 3 Ultra 550B A55B
Nemotron 3 Ultra 550B A55BOpen weights
NVIDIA · released 2026-06-04
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.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
| NvidiaOfficialnvidia/ | $0 | $0 | — | Official | Official docs |
Rrouting.runLowestnemotron-3-ultra | $0.1 | $0.1 | — | Lowest | Official docs |
KKilo Gatewaynvidia/ | $0.4 | $1.76 | $0.08 | Official docs | |
 DigitalOceannemotron-3-ultra-550b | $0.9 | $1.7 | $0.18 | Official docs | |
 CoreWeavenvidia/ | $0.5 | $2.15 | $0.1 | Official docs | |
EEden AIdeepinfra/ | $0.5 | $2.2 | $0.1 | Official docs | |
 DevPass (LLM Gateway)nemotron-3-ultra-550b | $0.5 | $2.2 | $0.1 | Official docs | |
 Basetennvidia/ | $0.6 | $2.4 | $0.12 | Official docs | |
 CommandCodenvidia/ | $0.6 | $2.4 | $0.12 | Official docs | |
NNanoGPTnvidia/ | $0.5 | $2.5 | $0.15 | Official docs | |
NNanoGPTnvidia/ | $0.5 | $2.5 | $0.15 | Official docs | |
 OpenRouternvidia/ | $0.6 | $2.4 | $0.12 | Official docs |
18 more listings
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
RRequestynvidia-nemotron-3-ultra | $0.5 | $2.5 | — | Official docs | |
 Vercel AI Gatewaynvidia/ | $0.6 | $2.4 | $0.12 | Official docs | |
 Ollama Cloudnemotron-3-ultra | $0.1 | $3 | $0.1 | Official docs | |
 Venice AInvidia-nemotron-3-ultra-550b-a55b | $0.625 | $3.125 | $0.1875 | Official docs | |
EEden AInebius/ | $1 | $3 | $1 | Official docs | |
 Nebius Token Factorynvidia/ | $1 | $3 | $0.12 | Official docs | |
EEden AIarkanecloud/ | $0.6 | $3.5 | $0.2 | Official docs | |
KKenarinemotron-3-ultra-550b-a55b | $0.685714 | $4.285714 | $0.068571 | Official docs | |
TThinking Machinesnvidia/ | $1.8 | $6.225 | $0.36 | Official docs | |
TThinking Machinesnvidia/ | $1.8 | $6.225 | $0.36 | Official docs | |
 Together AIDeprecatednvidia/ | $0.6 | $3.6 | $0.2 | Deprecated | Official docs |
 AIHubMixnemotron-3-ultra-550b-a55b-free | $0 | $0 | — | Official docs | |
BBothubnemotron-3-ultra-550b-a55b: | $0 | $0 | — | Official docs | |
KKilo Gatewaynvidia/ | $0 | $0 | — | Official docs | |
 OpenCodeDeprecatednemotron-3-ultra-free | $0 | $0 | $0 | Deprecated | Official docs |
| OpenRouternvidia/ | $0 | $0 | — | Official docs | |
RRequestynemotron-3-ultra-550b-a55b | $0 | $0 | — | Official docs | |
UUnoRouternemotron-3-ultra-550b-a55b: | $0 | $0 | — | Official docs |
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.
About
Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy
Description from models.dev.
Specs
- Type
- Text
- Context
- 1M
- Max output
- 65.5K
- Input
- Text
- Output
- Text
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- Yes
- Knowledge cutoff
- 2025-09
- Open weights
- Yes
- Released
- 2026-06-04
Source
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.