Same model, served by 1 provider.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
Mistral Original creatorDeprecated | magistral-medium-latest | standardQuantization not disclosed | $2.0 | $5.0 | — | $2.75 | Verified 7h ago · Changed 7h 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.
| Mistral | $300/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.