Same model, served by 2 providers.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
Azure AI Foundry | gpt-5.2-pro | batchglobal endpointQuantization not disclosed | $10.5 | $84.0 | — | $28.88 | Verified 5h ago · Changed 7h ago | |
Azure AI Foundry | gpt-5.2-pro | batchdata zone (US)Quantization not disclosed | $11.55 | $92.4 | — | $31.76 | Verified 5h ago · Changed 7h ago | |
Azure AI Foundry | gpt-5.2-pro | standardglobal endpointQuantization not disclosed | $21.0 | $168.0 | — | $57.75 | Verified 5h ago · Changed 7h ago | |
OpenAI Original creator | gpt-5.2-pro | standardQuantization not disclosed | $21.0 | $168.0 | — | $57.75 | Verified 7h ago · Changed 7h ago | |
Azure AI Foundry | gpt-5.2-pro | standarddata zone (US)Quantization not disclosed | $23.1 | $184.8 | — | $63.53 | Verified 5h 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.
| Azure AI Foundry global endpoint | $5,460/mo |
| OpenAI | $5,460/mo |
| Azure AI Foundry data zone (US) | $6,006/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.