Same model, served by 2 providers.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
Azure AI Foundry | gpt-5-pro | batchglobal endpointQuantization not disclosed | $7.5 | $60.0 | — | $20.63 | Verified 6h ago · Changed 8h ago | |
Azure AI Foundry | gpt-5-pro | batchdata zone (US)Quantization not disclosed | $8.25 | $66.0 | — | $22.69 | Verified 6h ago · Changed 8h ago | |
Azure AI Foundry | gpt-5-pro | standardglobal endpointQuantization not disclosed | $15.0 | $120.0 | — | $41.25 | Verified 6h ago · Changed 8h ago | |
OpenAI Original creator | gpt-5-pro | standardQuantization not disclosed | $15.0 | $120.0 | — | $41.25 | Verified 8h ago · Changed 8h ago | |
Azure AI Foundry | gpt-5-pro | standarddata zone (US)Quantization not disclosed | $16.5 | $132.0 | — | $45.38 | Verified 6h ago · Changed 8h 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.
| Azure AI Foundry global endpoint | $3,900/mo |
| OpenAI | $3,900/mo |
| Azure AI Foundry data zone (US) | $4,290/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.