Same model, served by 2 providers.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
Azure AI Foundry | gpt-5.4-mini | batchglobal endpointQuantization not disclosed | $0.375 | $2.25 | $0.037 | $0.844 | Verified 5h ago · Changed 7h ago | |
Azure AI Foundry | gpt-5.4-mini | batchdata zone (US)Quantization not disclosed | $0.412 | $2.48 | $0.041 | $0.928 | Verified 5h ago · Changed 7h ago | |
Azure AI Foundry | gpt-5.4-mini | standardglobal endpointQuantization not disclosed | $0.75 | $4.5 | $0.075 | $1.69 | Verified 5h ago · Changed 7h ago | |
OpenAI Original creator | gpt-5.4-mini | standardQuantization not disclosed | $0.75 | $4.5 | $0.075 | $1.69 | Verified 7h ago · Changed 7h ago | |
Azure AI Foundry | gpt-5.4-mini | standarddata zone (US)Quantization not disclosed | $0.825 | $4.95 | $0.083 | $1.86 | Verified 5h ago · Changed 7h ago | |
Azure AI Foundry | gpt-5.4-mini | priorityglobal endpointQuantization not disclosed | $1.5 | $9.0 | $0.15 | $3.38 | Verified 5h ago · Changed 7h ago | |
Azure AI Foundry | gpt-5.4-mini | prioritydata zone (US)Quantization not disclosed | $1.65 | $9.9 | $0.165 | $3.71 | 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 | $165/mo |
| OpenAI | $165/mo |
| Azure AI Foundry data zone (US) | $181.5/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.