Same model, served by 2 providers.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
Azure AI Foundry | o1 | batchglobal endpointQuantization not disclosed | $7.5 | $30.0 | — | $13.13 | Verified 6h ago · Changed 9h ago | |
Azure AI Foundry | o1 | batchdata zone (US)Quantization not disclosed | $8.25 | $33.0 | — | $14.44 | Verified 6h ago · Changed 9h ago | |
OpenAI Original creatorDeprecated | o1 | standardQuantization not disclosed | $15.0 | $60.0 | $7.5 | $26.25 | Verified 9h ago · Changed 9h 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.
| OpenAI | $2,700/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.