Nemotron 3 Ultra 550B A55B
As of Nov 22, 2026, the cheapest Nemotron 3 Ultra 550B A55B API price is $0.1 per 1M input tokens (routing.run) and $0.1 per 1M output tokens (routing.run). Nemotron 3 Ultra 550B A55B is offered by 16 providers in the nemotron-ultra family, open weights, reasoning enabled. 6 providers list it as a free-tier offer.
API pricing by provider
Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked. Seeing a wide range? Why the same LLM costs different amounts.
| routing.runopennemotron-3-ultra | Cheapest$0.1 | Cheapest$0.1 | — | — | 131k | — |
| Doublewordopennvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 | $0.5 | $2.2 | $0.125 | $0.625 | 1.0M | — |
| Eden AIopendeepinfra/nemotron-3-ultra-550b-a55b | $0.5 | $2.2 | $0.1 | — | 262k | — |
| Kilo Gatewayopennvidia/nemotron-3-ultra-550b-a55b | $0.5 | $2.2 | $0.1 | — | 262k | 4d agoout +25% |
| DevPass (LLM Gateway)opennemotron-3-ultra-550b | $0.5 | $2.2 | $0.1 | — | 1.0M | — |
| OpenRouteropennvidia/nemotron-3-ultra-550b-a55b | $0.5 | $2.2 | $0.1 | — | 262k | 4d agoout −8.3% |
| Requestyopennvidia-nemotron-3-ultra | $0.5 | $2.5 | — | — | 262k | — |
| CommandCodeopennvidia/nemotron-3-ultra-550b-a55b | $0.6 | $2.4 | $0.12 | — | 1.0M | — |
| Kelnopennvidia/nemotron-3-ultra-550b-a55b | $0.8 | $3 | $0.14 | — | 262k | — |
| Eden AIopennebius/nvidia/Nemotron-3-Ultra-550b-a55b | $1 | $3 | $1 | — | 1.0M | — |
| Nebius Token Factoryopennvidia/Nemotron-3-Ultra-550b-a55b | $1 | $3 | $0.12 | — | 1.0M | — |
| Kenariopennemotron-3-ultra-550b-a55b | $0.6857 | $4.29 | $0.0686 | — | 1.0M | 5d agoout +0.1% |
| Thinking Machinesopennvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 | $1.8 | $6.225 | $0.36 | — | 66k | — |
| Thinking Machinesopennvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16:peft:262144 | $1.8 | $6.225 | $0.36 | — | 262k | — |
| AIHubMixfreenemotron-3-ultra-550b-a55b-free | free | free | — | — | 1.0M | — |
| InferAllfreenvidia/nemotron-3-ultra-550b-a55b | free | free | — | — | 1.0M | — |
| Kenarifreenemotron-3-ultra-550b-a55b:free | free | free | — | — | 1.0M | — |
| Nvidiafreenvidia/nemotron-3-ultra-550b-a55b | free | free | — | — | 1.0M | — |
| Requestyfreenemotron-3-ultra-550b-a55b | free | free | — | — | 1.0M | — |
| UnoRouterfreenemotron-3-ultra-550b-a55b:free | free | free | — | — | 1.0M | — |
Nemotron 3 Ultra 550B A55B price history
Output price per 1M tokens since tracking began on Sep 10, 2026, for the 3 providers whose rate moved. Each step is a recorded change. All recent price changes.
| Date | Provider | 1M input | 1M output | Change |
|---|---|---|---|---|
| Kilo Gateway | $0.4 → $0.5 | $1.76 → $2.2 | +25% | |
| OpenRouter | $0.6 → $0.5 | $2.4 → $2.2 | −8.3% | |
| Kenari | $0.6857 → $0.6857 | $4.2857 → $4.29 | +0.1% | |
| Kenari | free → $0.6857 | free → $4.2857 | — | |
| Kilo Gateway | $0.5 → $0.4 | $2.2 → $1.76 | −20% | |
| OpenRouter | $0.5 → $0.6 | $2.2 → $2.4 | +9.1% | |
| OpenRouter | $0.6 → $0.5 | $2.4 → $2.2 | −8.3% | |
| OpenRouter | $0.625 → $0.6 | $3.125 → $2.4 | −23.2% | |
| OpenRouter | $0.6 → $0.625 | $2.4 → $3.125 | +30.2% | |
| OpenRouter | $0.625 → $0.6 | $3.125 → $2.4 | −23.2% |
Nemotron 3 Ultra 550B A55B pricing FAQ
What is the cheapest Nemotron 3 Ultra 550B A55B API?
As of Nov 22, 2026, routing.run has the lowest Nemotron 3 Ultra 550B A55B output price at $0.1 per 1M tokens, and routing.run has the lowest input price at $0.1 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.
How many providers offer Nemotron 3 Ultra 550B A55B?
16 providers list Nemotron 3 Ultra 550B A55B on Sovyron; 14 of them sell it at a metered per-token price.
Is Nemotron 3 Ultra 550B A55B free?
6 providers list a free-tier offer: AIHubMix, InferAll, Kenari, Nvidia, Requesty, UnoRouter. Free tiers usually have rate limits.
What is the context window of Nemotron 3 Ultra 550B A55B?
Nemotron 3 Ultra 550B A55B supports a 1.0M-token context window and up to 1.0M output tokens.
Token cost calculator
What a month costs at one provider's published rates. Enter the tokens you expect to send and receive; cached tokens use the cached-input price where the provider lists one, and count as ordinary input where it does not. See how much prompt caching saves and why output tokens cost more than input tokens.
Estimated
—