Same open weights, served by 1 provider.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra Deprecated, 2025-09-15 | mistralai/Mistral-7B-Instruct-v0.3 | standardFull precisionReduced context (33k of 66k) | $0.028 | $0.054 | โ | $0.035 | Verified 12h ago ยท Changed 40d 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 bfloat16 | $3.88/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.