Same open weights, served by 2 providers. Weights: nvidia/nemotron-3-ultra-550b-a55b.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
Fireworks AI | accounts/fireworks/models/nemotron-3-ultra-nvfp4 | standardQuantization not disclosedReduced context (262k of 1M) | $0.60 | $2.4 | $0.12 | $1.05 | Verified 9h ago · Changed 9h ago | |
Together AI | nvidia/nemotron-3-ultra-550b-a55b | standardQuantization not disclosedReduced context (512k of 1M) | $0.60 | $3.6 | $0.20 | $1.35 | Verified 9h ago · Changed 9h ago |
Same weights don't always mean identical outputs: quantization, context limits and serving stacks can change quality, especially for tool calling. Prices are USD per 1M tokens; hyperscaler prices are for the reference region shown.
| Fireworks AI | $108/mo |
| Together AI | $132/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.