# Qwen: Qwen3 VL 235B A22B Instruct

Provider: qwen  
Category: llm  
Model ID: `qwen/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...

## Specs

- Context length: 262144 tokens
- Max output: unknown tokens
- Modalities: text, image
- Released: 2025-09-23

## Pricing

- Input: $0.20 per million tokens
- Output: $0.88 per million tokens

## Providers

- **qwen** — ctx 262144, input $0.20/M, output $0.88/M

---
Last verified: 2026-04-23T23:46:29.618Z  
Canonical URL: https://switchy.build/models/qwen3-vl-235b-a22b-instruct