All Models

Qwen/Qwen3-VL-235B-A22B-Instruct

qwen Tool Calling Attachments Open Weights Structured Output

Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...

Providers 4
Released Sep 23, 2025
Input Modalities text, image
Output Modalities text
Tarsk Use coding

Benchmarks

20.8
Intelligence Index
16.5
Coding Index
70.7
Math Index

Available Providers (4)

Provider Model ID Input Cost Output Cost Context Max Output Docs
Kilo Gateway qwen/qwen3-vl-235b-a22b-instruct $0.20/MTok $0.88/MTok 262.1K 52.4K
SiliconFlow (China) Qwen/Qwen3-VL-235B-A22B-Instruct $0.30/MTok $1.50/MTok 262K 262K
Amazon Bedrock qwen.qwen3-vl-235b-a22b $0.30/MTok $1.50/MTok 262K 262K
SiliconFlow Qwen/Qwen3-VL-235B-A22B-Instruct $0.30/MTok $1.50/MTok 262K 262K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output