All Models

Qwen3.5-35B-A3B

qwen Reasoning Tool Calling Attachments Open Weights Structured Output

The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...

Providers 2
Released Feb 26, 2026
Input Modalities text, image, video
Output Modalities text
Tarsk Use coding

Benchmarks

37.1
Intelligence Index
30.3
Coding Index

Available Providers (2)

Provider Model ID Input Cost Output Cost Context Max Output Docs
NovitaAI qwen/qwen3.5-35b-a3b $0.25/MTok $2.00/MTok 262.1K 65.5K
Mixlayer qwen/qwen3.5-35b-a3b $0.25/MTok $1.30/MTok 262.1K 262.1K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output