Same model, served by 2 providers.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
Azure AI Foundry | gpt-4.1 | standardglobal endpointQuantization not disclosed | $2.0 | $8.0 | $0.50 | $3.5 | Verified 5h ago · Changed 7h ago | |
OpenAI Original creator | gpt-4.1 | standardQuantization not disclosed | $2.0 | $8.0 | $0.50 | $3.5 | Verified 7h ago · Changed 7h ago | |
Azure AI Foundry | gpt-4.1 | standardeastusQuantization not disclosed | $2.2 | $8.8 | $0.55 | $3.85 | Verified 5h ago · Changed 7h ago | |
Azure AI Foundry | gpt-4.1 | standarddata zone (US)Quantization not disclosed | $2.2 | $8.8 | $0.55 | $3.85 | 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 | $360/mo |
| OpenAI | $360/mo |
| Azure AI Foundry eastus | $396/mo |
| Azure AI Foundry data zone (US) | $396/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.