Command Palette
Search for a command to run

Qwen3 VL 235B A22B Instruct

by Qwen

Specifications

Input
Output
Context window
131K tokens
Released
Sep 2025

Performance

Speed
57 t/s
TTFT
680 ms
Latency
1.6s
Intelligence

Pricing

Input
€0.20
per 1M tokens
Output
€1.80
per 1M tokens

About this model

Qwen3 VL 235B A22B Instruct is Alibaba's vision-language MoE model with 235B total / 22B active parameters. Combines state-of-the-art text and vision understanding with excellent performance on multimodal reasoning tasks.

Technical specifications

Capabilities
Input modalities
Output modalities
Reasoning
No

Knowledge horizon

Released Sep 2025
Today
Since release 9 mo

See also

Add Model to Comparison
Search for a model to add
Command Palette
Search for a command to run