Compare model prices
Input, output, cached and batch prices, every route and a month of tokens, side by side.
Qwen3 235B A22B Instruct 2507A month of tokens
100M input and 20M output tokens, list price. Use your own numbers.
Side by side
| Qwen3 235B A22B Instruct 2507 | |
|---|---|
| Input per 1M | $0.15 |
| Output per 1M | $0.598 |
| Cached input | n/a |
| Batch in / out | n/a |
| Blended (3:1) | $0.262 |
| Context | 262K |
| Routes | 9 |
| Released | Jul 21, 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
Qwen3 235B A22B Instruct 2507
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
| GMICloud fp8, cheapest · cached $0.018 | $0.087 | $0.35 | $0.087 / $0.35-41% vs list | $0.018 | -41% vs list |
 DeepInfrafp8 | $0.09 | $0.55 | $0.09 / $0.55-22% vs list | n/a | -22% vs list |
 Novita AIfp8 | $0.09 | $0.58 | $0.09 / $0.58-19% vs list | n/a | -19% vs list |
| Qwen (Alibaba) API The lab's own API | $0.15 | $0.598 | $0.15 / $0.598List price | n/a | List price |
 Venicefp8 | $0.15 | $0.75 | $0.15 / $0.75+15% vs list | n/a | +15% vs list |
 Nebiusfp8 | $0.2 | $0.6 | $0.2 / $0.6+15% vs list | n/a | +15% vs list |
 Parasailfp8 · cached $0.05 | $0.14 | $0.8 | $0.14 / $0.8+17% vs list | $0.05 | +17% vs list |
| StreamLake Default region | $0.21 | $0.84 | $0.21 / $0.84+40% vs list | n/a | +40% vs list |
 Google Vertex AIus-south1 | $0.22 | $0.88 | $0.22 / $0.88+47% vs list | n/a | +47% 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.