Same open weights, served by 1 provider.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra | NousResearch/Hermes-3-Llama-3.1-70B | flexFP80.8× standard | $0.56 | $0.56 | — | $0.56 | Verified 6h ago · Changed 8h ago | |
DeepInfra | NousResearch/Hermes-3-Llama-3.1-70B | standardFP8 | $0.70 | $0.70 | — | $0.70 | Verified 6h ago · Changed 8h ago | |
DeepInfra | NousResearch/Hermes-3-Llama-3.1-70B | priorityFP81.5× standard | $1.05 | $1.05 | — | $1.05 | Verified 6h ago · Changed 8h 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.
| DeepInfra fp8 | $84/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.