Same model, served by 2 providers.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
Mistral Original creator | codestral-2508 | standardQuantization not disclosed | $0.30 | $0.90 | $0.03 | $0.45 | Verified 6h ago · Changed 6h ago | |
Google Vertex AI | codestral-2 | standardQuantization not disclosedReduced context (128k of 256k) | $0.30 | $0.90 | — | $0.45 | Verified 6h ago · Changed 6h 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 | $48/mo |
| Google Vertex AI | $48/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.