Home / NVIDIA / Nemotron / Nemotron 3 Ultra 550B A55B
Nemotron 3 Ultra 550B A55B API price
nvidia/nemotron-3-ultra-550b-a55b
The cheapest Nemotron 3 Ultra 550B A55B API is $0.50/M input at DeepInfra (via OpenRouter) - all 4 providers compared below, per 1M tokens.
FlagshipNVIDIA262K context4 sellers
Input
$0.50
per 1M tokens · DeepInfra (via OpenRouter)
up to $0.625
Output
$2.20
per 1M tokens · DeepInfra (via OpenRouter)
up to $3.60
Where to buy it
Cheapest Nemotron 3 Ultra 550B A55B API providers compared - 4 sellers, from $0.50/M.
| Provider | Input $/M | Output $/M | Cached in | Uptime |
|---|---|---|---|---|
| DeepInfra (via OpenRouter)fp4 | 0.500cheapest | 2.20 | 0.100 | 100% |
| BaseTen (via OpenRouter)fp4 | 0.600 | 2.40 | 0.120 | 98.2% |
| Venice (via OpenRouter)fp8 | 0.625 | 3.12 | 0.188 | 100% |
| Together AI (inference host) | 0.600 | 3.60 | 0.200 | - |
1.2× between the cheapest and the dearest of 4 sellers.
Against its tier
- This model$2.70
- Cheapest · GLM 5.3 Flash$0.29
- Tier median · Grok 4.6$8.00
- Dearest · GPT 5.5 Pro (04-23 snapshot)$330.00
#6 of 31 flagship · cheaper than 83%
Details
- Context window
- 262K262,144 tokens
- Developer
- NVIDIA
- Intelligence
- 38.3Reasoning
- Sellers
- 41.2× spread
- Cached input
- $0.10where the source publishes one
- Cheapest at
- DeepInfra (via OpenRouter)
- Combined
- $2.70in + out per 1M
- Last checked
- 2026-08-28
- Availability
- 100.00%median of 3 OpenRouter endpoints, last 30 min