Same model, served by 2 providers.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
Azure AI Foundry | gpt-5-nano | batchglobal endpointQuantization not disclosed | $0.025 | $0.20 | $0.0025 | $0.069 | Verified 5h ago · Changed 7h ago | |
Azure AI Foundry | gpt-5-nano | batchdata zone (US)Quantization not disclosed | $0.028 | $0.22 | $0.0027 | $0.076 | Verified 5h ago · Changed 7h ago | |
Azure AI Foundry | gpt-5-nano | standardglobal endpointQuantization not disclosed | $0.05 | $0.40 | $0.0050 | $0.138 | Verified 5h ago · Changed 7h ago | |
OpenAI Original creator | gpt-5-nano | standardQuantization not disclosed | $0.05 | $0.40 | $0.0050 | $0.138 | Verified 7h ago · Changed 7h ago | |
Azure AI Foundry | gpt-5-nano | standarddata zone (US)Quantization not disclosed | $0.055 | $0.44 | $0.0055 | $0.151 | 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 | $13/mo |
| OpenAI | $13/mo |
| Azure AI Foundry data zone (US) | $14.3/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.