Qwen: Qwen-Max qwen
Bottom Line
Qwen: Qwen-Max : $1.04/1M input, $4.16/1M output, 33K context. Qwen-Max, based on Qwen2.5, provides the best inference performance among [Qwen models](/qwen), especially for complex multi-step tasks. It's a large-scale MoE model that has been pretrained on over 20 trillion...
API Pricing (per 1M tokens)
| Input | $1.04 |
| Output | $4.16 |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $1.82 |
Specs & Performance
| Context Length | 33K |
| Max Output | 8K |
| Intelligence | — |
| Coding | — |
| Math | — |
| Speed | — |
| TTFT | — |
| CPS Grade | — |
| Input / Output Modalities | text → text |
More from qwen
Looking for cheaper alternatives?
Find the cheapest model by task, or compare two models head-to-head.
FAQ
How much does the Qwen: Qwen-Max API cost?
Qwen: Qwen-Max costs $1.04/1M input tokens and $4.16/1M output tokens. Blended cost at a 3:1 ratio is about $1.82/1M tokens.
What is the context window of Qwen: Qwen-Max ?
Qwen: Qwen-Max supports a 33K token context window with up to 8K output tokens.
Is Qwen: Qwen-Max worth it?
Qwen: Qwen-Max has a CPS grade of — (score —), intelligence index —, coding index —. Use the compare page to benchmark against rivals.