infery
← All models

Qwen3.5 397B A17B

qwen3.5-397b-a17b

Chat & Textby Qwen

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. 262,144 token context window. Higher uptime with 11 providers. Includes independent benchmarks from Artificial Analysis.

chatstreamingvisiontoolsjson mode

Details

Accepts
text
Context window
262K tokens

Pricing

Input
68.75 cr / 1M tokens
Output
438 cr / 1M tokens
Cached input
28.13 cr / 1M tokens

Prices in credits (1 credit = $0.01).

Data schema

approximate

Input

FieldTypeDescription
promptrequiredstringThe text prompt.

Output

FieldTypeDescription
textstringGenerated text (choices[0].message.content).