All Models

Qwen 3.5 397B A17B

qwen Reasoning Tool Calling Attachments Open Weights Structured Output

Qwen vision-language model for visual reasoning, documents, and agent tasks

Providers 2
Released Feb 1, 2026
Input Modalities text, image, video
Output Modalities text
Tarsk Use coding

Benchmarks

34.3
Intelligence Index
48.2
Coding Index

Available Providers (2)

Provider Model ID Input Cost Output Cost Context Max Output Docs
Deep Infra Qwen/Qwen3.5-397B-A17B $0.45/MTok $3/MTok 262.1K 81.9K
DigitalOcean qwen3.5-397b-a17b $0.55/MTok $3.50/MTok 131.1K 131.1K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output