Compare model prices
Input, output, cached and batch prices, every route and a month of tokens, side by side.
Qwen3.5-122B-A10BQwen3.8 Max PrimeA month of tokens
100M input and 20M output tokens, list price. Use your own numbers.
Side by side
| Qwen3.5-122B-A10B | Qwen3.8 Max Prime | |
|---|---|---|
| Input per 1M | $0.26 | $4 |
| Output per 1M | $2.08 | $12 |
| Cached input | n/a | $0.5 |
| Batch in / out | n/a | n/a |
| Blended (3:1) | $0.715 | $6 |
| Context | 262K | 1M |
| Routes | 5 | 1 |
| Released | Feb 25, 2026 | Sep 23, 2026 |
| Leadersboard score | n/a | n/a |
On the price map
Size: context window, 8K to 2MEqual blended cost (3:1) 245 models, lower left is cheaper
Every route
Qwen3.5-122B-A10B
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
| Qwen (Alibaba) API The lab's own API | $0.26 | $2.08 | $0.26 / $2.08List price | n/a | List price |
 SiliconFlowfp8 | $0.26 | $2.08 | $0.26 / $2.08Same as list | n/a | Same as list |
 DeepInfrafp4 | $0.29 | $2.4 | $0.29 / $2.4+14% vs list | n/a | +14% vs list |
| AtlasCloud fp8 · cached $0.3 | $0.3 | $2.4 | $0.3 / $2.4+15% vs list | $0.3 | +15% vs list |
 Novita AIbf16 | $0.4 | $3.2 | $0.4 / $3.2+54% vs list | n/a | +54% vs list |
Qwen3.8 Max Prime
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
| Qwen (Alibaba) API The lab's own API · cached $0.5 | $4 | $12 | $4 / $12List price | $0.5 | 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.