Compare model prices
Input, output, cached and batch prices, every route and a month of tokens, side by side.
GPT-4 TurboA month of tokens
100M input and 20M output tokens, list price. Use your own numbers.
Side by side
| GPT-4 Turbo | |
|---|---|
| Input per 1M | $10 |
| Output per 1M | $30 |
| Cached input | n/a |
| Batch in / out | $5 / $15 |
| Blended (3:1) | $15 |
| Context | 128K |
| Routes | 1 |
| Released | Apr 9, 2024 |
| 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-4 Turbo
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
| OpenAI API The lab's own API | $10 | $30 | $10 / $30List price | n/a | List price |
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.