Skip to main content
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

ProviderProvider model IDProtocolContextMax outputInputOutputCapabilitiesNotesPricingStreaming
OpenRouterqwen/qwen3-vl-235b-a22b-instructopenai_chat262K33K
AttachmentsTool callStructuredTemperature
Hugging Face: Qwen/Qwen3-VL-235B-A22B-Instruct
input $0.21/M · output $1.9/M
cache read $0.1/M
Yes
TensorXqwen/qwen3-vl-235b-a22b-instructopenai_chat262K33K
AttachmentsTool callTemperature
-
input $0.21/M · output $1.9/M
cache read $0.053/M · cache write $0.263/M
Yes
Kilo Gatewayqwen/qwen3-vl-235b-a22b-instructopenai_chat262K33K
AttachmentsTool callStructuredTemperature
-
input $0.26/M · output $1.04/M
Yes
NovitaAIqwen/qwen3-vl-235b-a22b-instructopenai_chat262K33K
AttachmentsTool callStructuredTemperature
-
input $0.3/M · output $1.5/M
Yes
Alibabaqwen3-vl-235b-a22b-instructcustom262K33K
---Yes

FAQ