All Models

Qwen 3.5 397B

qwenReasoningTool CallingAttachmentsOpen WeightsStructured Output

Large open Qwen multimodal MoE for visual agents and long technical tasks

Providers1
ReleasedFeb 16, 2026
Input Modalitiestext, image, video
Output Modalitiestext
Tarsk Usecoding

Available Providers (1)

ProviderModel IDInput CostOutput CostContextMax OutputDocs
Venice AIqwen3-5-397b-a17b$0.75/MTok$4.50/MTok128K32.8K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output