Compare model prices
Input, output, cached and batch prices, every route and a month of tokens, side by side.
GPT-5.1A month of tokens
100M input and 20M output tokens, list price. Use your own numbers.
Side by side
| GPT-5.1 | |
|---|---|
| Input per 1M | $1.25 |
| Output per 1M | $10 |
| Cached input | $0.125 |
| Batch in / out | $0.625 / $5 |
| Blended (3:1) | $3.44 |
| Context | 400K |
| Routes | 5 |
| Released | Nov 13, 2025 |
| Leadersboard score | 3 (#39) |
On the price map
Size: context window, 8K to 2MEqual blended cost (3:1) 243 models, lower left is cheaper
Every route
GPT-5.1
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
| OpenAI flex, cheapest · cached $0.063 | $0.625 | $5 | $0.625 / $5-50% vs list | $0.063 | -50% vs list |
| OpenAI API The lab's own API · cached $0.125 | $1.25 | $10 | $1.25 / $10List price | $0.125 | List price |
 Azure AI FoundryDefault region · cached $0.13 | $1.25 | $10 | $1.25 / $10Same as list | $0.13 | Same as list |
| Azure AI Foundry swedencentral · cached $0.143 | $1.38 | $11 | $1.38 / $11+10% vs list | $0.143 | +10% vs list |
| OpenAI fast · cached $0.25 | $2.5 | $20 | $2.5 / $20+100% vs list | $0.25 | +100% vs list |
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.