Same open weights, served by 2 providers.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra Deprecated, 2025-09-11 | mistralai/Devstral-Small-2507 | standardFP8 | $0.07 | $0.28 | — | $0.123 | Verified 6h ago · Changed 8h ago | |
Mistral Original creatorDeprecated | devstral-small-2507 | standardQuantization not disclosed | $0.10 | $0.30 | — | $0.15 | Verified 8h 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 | $12.6/mo |
| Mistral | $16/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.