Compare model prices
Input, output, cached and batch prices, every route and a month of tokens, side by side.
GPT-5.2A month of tokens
100M input and 20M output tokens, list price. Use your own numbers.
Side by side
| GPT-5.2 | |
|---|---|
| Input per 1M | $1.75 |
| Output per 1M | $14 |
| Cached input | $0.175 |
| Batch in / out | $0.875 / $7 |
| Blended (3:1) | $4.81 |
| Context | 400K |
| Routes | 4 |
| Released | Dec 10, 2025 |
| Leadersboard score | n/a |
On the price map
Size: context window, 8K to 2MEqual blended cost (3:1) 245 models, lower left is cheaper
Every route
GPT-5.2
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
| OpenAI flex, cheapest · cached $0.087 | $0.875 | $7 | $0.875 / $7-50% vs list | $0.087 | -50% vs list |
| OpenAI API The lab's own API · cached $0.175 | $1.75 | $14 | $1.75 / $14List price | $0.175 | List price |
 Azure AI FoundryDefault region · cached $0.175 | $1.75 | $14 | $1.75 / $14Same as list | $0.175 | Same as list |
| OpenAI fast · cached $0.35 | $3.5 | $28 | $3.5 / $28+100% vs list | $0.35 | +100% vs list |
Sources: OpenRouter's public model catalog and each provider's own pricing page, read every morning at 05:00 UTC; gateway fees re-read every Monday. List prices: your contract may differ. Logos via logo.dev; trademarks belong to their owners.