Compare model prices
Input, output, cached and batch prices, every route and a month of tokens, side by side.
GPT-4.1A month of tokens
100M input and 20M output tokens, list price. Use your own numbers.
Side by side
| GPT-4.1 | |
|---|---|
| Input per 1M | $2 |
| Output per 1M | $8 |
| Cached input | $0.5 |
| Batch in / out | $1 / $4 |
| Blended (3:1) | $3.5 |
| Context | 1.05M |
| Routes | 4 |
| Released | Apr 14, 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-4.1
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
| OpenAI API The lab's own API · cached $0.5 | $2 | $8 | $2 / $8List price | $0.5 | List price |
 Azure AI FoundryDefault region · cached $0.5 | $2 | $8 | $2 / $8Same as list | $0.5 | Same as list |
| Azure AI Foundry swedencentral · cached $0.55 | $2.2 | $8.8 | $2.2 / $8.8+10% vs list | $0.55 | +10% vs list |
 Snowflake Cortex AI (AI_COMPLETE)From the platform pricing page | $2.4 | $9.6 | $2.4 / $9.6+20% vs list | n/a | +20% 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.