gpt-5.1 pricing
gpt-5.1 by OpenAI is sold on OpenAI API and Microsoft Foundry (Azure), at the same lowest price on each: $1.25 per million input tokens and $10.00 per million output tokens. Batch, cache and in-region prices differ below.
Price on each platform
| Platform | Input | Output | Cached input | Batch input / output |
|---|---|---|---|---|
| OpenAI API | $1.25 | $10.00 | $0.125 | $0.625 / $5.00 |
| Microsoft Foundry (Azure) | $1.25 | $10.00 | $0.125 | $0.625 / $5.00 |
The lowest standard price on each platform, in USD per 1M tokens.
OpenAI API
| Tier | Runs in | Input | Output | Cached input |
|---|---|---|---|---|
| Standard | Anywhere | $1.25 | $10.00 | $0.125 |
| Batch | Anywhere | $0.625 | $5.00 | $0.0625 |
| Flex | Anywhere | $0.625 | $5.00 | $0.0625 |
| Priority | Anywhere | $2.50 | $20.00 | $0.25 |
Microsoft Foundry (Azure)
| Tier | Runs in | Input | Output | Cached input |
|---|---|---|---|---|
| Standard | Global (25 regions) | $1.25 | $10.00 | $0.125 |
| Standard | Geography (data zone) (14 regions) | $1.375 | $11.00 | $0.1375 |
| Standard | Geography (data zone) (9 regions) | $1.50 | $12.00 | $0.15 |
| Batch | Global (25 regions) | $0.625 | $5.00 | $0.0625 |
| Batch | Geography (data zone) (14 regions) | $0.6875 | $5.50 | $0.0688 |
| Batch | Geography (data zone) (9 regions) | $0.75 | $6.00 | $0.075 |
| Priority | Global (24 regions) | $2.50 | $20.00 | $0.25 |
| Priority | Geography (data zone) (13 regions) | $2.75 | $22.00 | $0.275 |
More OpenAI models
codex-mini · gpt-4-8k · gpt-4-32k · gpt-4-turbo-128k · gpt-4-turbo-vision-128k · gpt-4.1 · gpt-4.1-mini · gpt-4.1-nano · gpt-4.5-0227 · gpt-4o · gpt-4o-0513 · gpt-4o-0806 · gpt-4o-1120 · gpt-4o-mini · gpt-4o-mini-0718 · gpt-5 · gpt-5-chat · gpt-5-codex · gpt-5-mini · gpt-5-nano · gpt-5-pro · gpt-5.1-chat · gpt-5.1-codex · gpt-5.1-codex-max
Prices in USD per 1 million tokens, from OpenAI and Anthropic's pricing pages, the AWS Price List API (Bedrock) and the Azure Retail Prices API (Microsoft Foundry). Cloud prices are the lowest in any region; global deployments can run anywhere.
Prices as of 12 Nov 2026. All AI models