All Models

Qwen/Qwen3-235B-A22B-Instruct-2507

qwen Reasoning Tool Calling Open Weights Structured Output

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,...

Providers 3
Released Apr 1, 2025
Input Modalities text
Output Modalities text
Tarsk Use coding

Benchmarks

25
Intelligence Index
22.1
Coding Index
71.7
Math Index

Available Providers (3)

Provider Model ID Input Cost Output Cost Context Max Output Docs
Kilo Gateway qwen/qwen3-235b-a22b-2507 $0.07/MTok $0.10/MTok 262.1K 52.4K
SiliconFlow (China) Qwen/Qwen3-235B-A22B-Instruct-2507 $0.09/MTok $0.60/MTok 262K 262K
SiliconFlow Qwen/Qwen3-235B-A22B-Instruct-2507 $0.09/MTok $0.60/MTok 262K 262K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output