Qwen: Qwen3.5 397B A17B
- by qwen
- qwen/qwen3.5-397b-a17b
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...
What the numbers mean
- Context window262,144 tokens
- How much the model can read in one request, counting your prompt, any files and the conversation so far. That is about 200,000 words, or 393 pages.
- Max output64,000 tokens
- The longest single reply it can write: about 48,000 words.
- Input price$0.6 per million tokens
- What you pay for everything the model reads. A 1,000-word prompt costs less than a cent.
- Output price$3.6 per million tokens
- What you pay for everything the model writes. Output usually costs more than input. A 500-word answer costs less than a cent.
- Modalitiestext, image, video in, text out
- The kinds of content it accepts and the kinds it produces. A model that takes images in can read a screenshot; one that only puts text out cannot draw.
Supported parameters
The settings you can pass with a request. A model that lists tools can call functions; one that lists structured_outputs can be held to a JSON schema.
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penalty