Same model, served by 2 providers.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
Azure AI Foundry | gpt-5-mini | batchglobal endpointQuantization not disclosed | $0.125 | $1.0 | $0.013 | $0.344 | Verified 6h ago · Changed 8h ago | |
Azure AI Foundry | gpt-5-mini | batchdata zone (US)Quantization not disclosed | $0.138 | $1.1 | $0.014 | $0.378 | Verified 6h ago · Changed 8h ago | |
Azure AI Foundry | gpt-5-mini | standardglobal endpointQuantization not disclosed | $0.25 | $2.0 | $0.025 | $0.688 | Verified 6h ago · Changed 8h ago | |
OpenAI Original creator | gpt-5-mini | standardQuantization not disclosed | $0.25 | $2.0 | $0.025 | $0.688 | Verified 8h ago · Changed 8h ago | |
Azure AI Foundry | gpt-5-mini | standarddata zone (US)Quantization not disclosed | $0.275 | $2.2 | $0.028 | $0.756 | Verified 6h ago · Changed 8h ago | |
Azure AI Foundry | gpt-5-mini | priorityglobal endpointQuantization not disclosed | $0.45 | $3.6 | $0.045 | $1.24 | Verified 6h ago · Changed 8h ago | |
Azure AI Foundry | gpt-5-mini | prioritydata zone (US)Quantization not disclosed | $0.495 | $3.96 | $0.05 | $1.36 | 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 | $65/mo |
| OpenAI | $65/mo |
| Azure AI Foundry data zone (US) | $71.5/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.