ALAlibaba/ Qwen
Qwen3 VL 235B A22B Instruct
alibaba/qwen3-vl-235b-a22b-instruct
Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...
Model information
Released
2025-09-23
Context window
262K
Max output
33K
Model parameters
236B
Weights
Open
Modalities
Input
ImageText
Output
Text
Identity
- Version
- qwen3-vl-235b-a22b-instruct
- Knowledge cutoff
- 2025-03-31
- License
- Apache-2.0
Resources
Capabilities
Open weightStructuredTemperatureTool call
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| OpenRouter | qwen/qwen3-vl-235b-a22b-instruct | openai_chat | 262K | 33K | AttachmentsTool callStructuredTemperature | Hugging Face: Qwen/Qwen3-VL-235B-A22B-Instruct | input $0.21/M · output $1.9/M cache read $0.1/M | Yes | ||
| TensorX | qwen/qwen3-vl-235b-a22b-instruct | openai_chat | 262K | 33K | AttachmentsTool callTemperature | - | input $0.21/M · output $1.9/M cache read $0.053/M · cache write $0.263/M | Yes | ||
| Kilo Gateway | qwen/qwen3-vl-235b-a22b-instruct | openai_chat | 262K | 33K | AttachmentsTool callStructuredTemperature | - | input $0.26/M · output $1.04/M | Yes | ||
| NovitaAI | qwen/qwen3-vl-235b-a22b-instruct | openai_chat | 262K | 33K | AttachmentsTool callStructuredTemperature | - | input $0.3/M · output $1.5/M | Yes | ||
| Alibaba | qwen3-vl-235b-a22b-instruct | custom | 262K | 33K | - | - | - | Yes |