All Models

Qwen3.5-122B-A10B

qwen Reasoning Tool Calling Attachments Open Weights Structured Output

The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...

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

Benchmarks

41.6
Intelligence Index
34.7
Coding Index

Available Providers (2)

Provider Model ID Input Cost Output Cost Context Max Output Docs
NovitaAI qwen/qwen3.5-122b-a10b $0.40/MTok $3.20/MTok 262.1K 65.5K
Mixlayer qwen/qwen3.5-122b-a10b $0.40/MTok $3.20/MTok 262.1K 262.1K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output