Compare model prices
Input, output, cached and batch prices, every route and a month of tokens, side by side.
GPT-5 MiniA month of tokens
100M input and 20M output tokens, list price. Use your own numbers.
Side by side
| GPT-5 Mini | |
|---|---|
| Input per 1M | $0.25 |
| Output per 1M | $2 |
| Cached input | $0.025 |
| Batch in / out | $0.125 / $1 |
| Blended (3:1) | $0.688 |
| Context | 400K |
| Routes | 4 |
| Released | Aug 7, 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 Mini
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
| OpenAI flex, cheapest · cached $0.013 | $0.125 | $1 | $0.125 / $1-50% vs list | $0.013 | -50% vs list |
| OpenAI API The lab's own API · cached $0.025 | $0.25 | $2 | $0.25 / $2List price | $0.025 | List price |
 Azure AI FoundryDefault region · cached $0.03 | $0.25 | $2 | $0.25 / $2Same as list | $0.03 | Same as list |
| Azure AI Foundry swedencentral · cached $0.033 | $0.275 | $2.2 | $0.275 / $2.2+10% vs list | $0.033 | +10% 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.