Same open weights, served by 1 provider.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra | mistralai/Mistral-Small-3.2-24B-Instruct-2506 | flexFP80.8× standard | $0.06 | $0.16 | — | $0.085 | Verified 1h ago · Changed 36h ago | |
DeepInfra | mistralai/Mistral-Small-3.2-24B-Instruct-2506 | standardFP8 | $0.075 | $0.20 | — | $0.106 | Verified 1h ago · Changed 36h ago | |
DeepInfra | mistralai/Mistral-Small-3.2-24B-Instruct-2506 | priorityFP81.5× standard | $0.113 | $0.30 | — | $0.159 | Verified 1h ago · Changed 36h 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 | $11.5/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.