Qwen: Qwen3.5 397B A17Bqwen
Qwen: Qwen3.5 397B A17B: $0.50/1M input, $3.60/1M output, 262K context, CPS grade B. The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...
API Pricing (per 1M tokens)
| Input | $0.50 |
| Output | $3.60 |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $1.27 |
Specs & Performance
| Context Length | 262K |
| Max Output | 236K |
| Intelligence | 18 |
| Coding | 48 |
| Math | — |
| Speed | 58 tok/s |
| TTFT | 1.52s |
| CPS Grade | B |
| Input / Output Modalities | text, image, video → 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: Qwen3.5 397B A17B API cost?
Qwen: Qwen3.5 397B A17B costs $0.50/1M input tokens and $3.60/1M output tokens. Blended cost at a 3:1 ratio is about $1.27/1M tokens.
What is the context window of Qwen: Qwen3.5 397B A17B?
Qwen: Qwen3.5 397B A17B supports a 262K token context window with up to 236K output tokens.
Is Qwen: Qwen3.5 397B A17B worth it?
Qwen: Qwen3.5 397B A17B has a CPS grade of B (score 58), intelligence index 18, coding index 48. Use the compare page to benchmark against rivals.