Back to Models

Qwen: Qwen3 235B A22B Instruct 2507

qwen3-235b-a22b-2507

Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...

Modalities

Input

text

Output

text
Pricing
Cost per 1 million tokens
Input
$0.108
Output
$0.12
Model Specs
Context Window
262,144
Max Output
16,384
Release Date
2025-07-21
Knowledge Cutoff
2025-06-30
Capabilities
Reasoning
Tool Calling
Vision

Last Updated: 2025-07-21

Provider: