All Models
qwen3-vl-235b-a22b
Qwen3 VL 235B A22B is a 235B-parameter MoE vision-language flagship model (≈22B active) designed for frontier-level multimodal understanding across text, images, documents, and long videos.
Available Providers (3)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 Alibaba (China) | qwen3-vl-235b-a22b | $0.29/MTok | $1.15/MTok | 131.1K | 32.8K | |
 Cortecs | qwen3-vl-235b-a22b | $0.62/MTok | $3.12/MTok | 256K | 256K | |
 Alibaba | qwen3-vl-235b-a22b | $0.70/MTok | $2.80/MTok | 131.1K | 32.8K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output