Qwen: Qwen3 VL 235B A22B Instruct

by Qwen

0 stars
Context 131K tokens
Modalities Text, Image → Text
Max Output 32,768
Input Price $0.30 / million tokens
Output Price $1.50 / million tokens

Overview

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 extractio...

Key Features

  • Multimodal capabilities (Text, Image → Text)
  • 131K tokens context window
  • Up to 32,768 output tokens
  • API access available

Model Information

Developer:

Qwen

Release Date:

September 23, 2025

Context Window:

131K tokens

Modalities:

Text, Image → Text

Pricing

Input Tokens $0.30 / million tokens
Output Tokens $1.50 / million tokens
Get API Key

Discussion

No comments yet. Be the first to share your thoughts about this model!