Same model, served by 2 providers.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
Azure AI Foundry | gpt-5.1 | batchglobal endpointQuantization not disclosed | $0.625 | $5.0 | $0.063 | $1.72 | Verified 6h ago · Changed 8h ago | |
Azure AI Foundry | gpt-5.1 | batchdata zone (US)Quantization not disclosed | $0.688 | $5.5 | $0.069 | $1.89 | Verified 6h ago · Changed 8h ago | |
Azure AI Foundry | gpt-5.1 | standardglobal endpointQuantization not disclosed | $1.25 | $10.0 | $0.125 | $3.44 | Verified 6h ago · Changed 8h ago | |
OpenAI Original creator | gpt-5.1 | standardQuantization not disclosed | $1.25 | $10.0 | $0.125 | $3.44 | Verified 8h ago · Changed 8h ago | |
Azure AI Foundry | gpt-5.1 | standarddata zone (US)Quantization not disclosed | $1.38 | $11.0 | $0.138 | $3.78 | Verified 6h ago · Changed 8h ago | |
Azure AI Foundry | gpt-5.1 | priorityglobal endpointQuantization not disclosed | $2.5 | $20.0 | $0.25 | $6.88 | Verified 6h ago · Changed 8h ago | |
Azure AI Foundry | gpt-5.1 | prioritydata zone (US)Quantization not disclosed | $2.75 | $22.0 | $0.275 | $7.56 | 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 | $325/mo |
| OpenAI | $325/mo |
| Azure AI Foundry data zone (US) | $357.5/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.