Back to Models

Qwen: Qwen3 VL 235B A22B Instruct

qwen3-vl-235b-a22b-instruct

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...

Modalities

Input

textimage

Output

text
Pricing
Cost per 1 million tokens
Input
$0.24
Output
$1.056
Model Specs
Context Window
262,144
Max Output
52,429
Release Date
2025-09-23
Knowledge Cutoff
Capabilities
Reasoning
Tool Calling
Vision

Last Updated: 2026-01-10

Provider: