Same open weights, served by 1 provider. Weights: mistralai/Mistral-Small-24B-Instruct-2501.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra | mistralai/Mistral-Small-24B-Instruct-2501 | flexFP80.8× standard | $0.04 | $0.064 | — | $0.046 | Verified 6h ago · Changed 8h ago | |
DeepInfra | mistralai/Mistral-Small-24B-Instruct-2501 | standardFP8 | $0.05 | $0.08 | — | $0.058 | 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 | $6.6/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.