All Models

Qwen3 VL 235B A22B Instruct

qwenTool CallingAttachmentsOpen WeightsStructured Output

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...

Providers18
ReleasedSep 15, 2025
Input Modalitiestext, image, video
Output Modalitiestext
Tarsk Usecoding

Available Providers (18)

ProviderModel IDInput CostOutput CostContextMax OutputDocs
LLM Gatewaydeepinfra/qwen3-vl-235b-a22b-instruct$0.20/MTok$0.88/MTok262.1K32.8K
DevPass (LLM Gateway)qwen3-vl-235b-a22b-instruct$0.20/MTok$0.88/MTok262.1K8.2K
Deep InfraQwen/Qwen3-VL-235B-A22B-Instruct$0.20/MTok$0.88/MTok262.1K32.8K
OpenRouterqwen/qwen3-vl-235b-a22b-instruct$0.21/MTok$1.90/MTok262.1K32.8K
Kilo Gatewayqwen/qwen3-vl-235b-a22b-instruct$0.26/MTok$1.04/MTok131.1K32.8K
Merge Gatewayqwen/qwen3-vl-235b-a22b-instruct$0.29/MTok$1.15/MTok131.1K32.8K
NanoGPTqwen/qwen3-vl-235b-a22b-instruct$0.30/MTok$1.20/MTok131.1K32.8K
SiliconFlow (China)Qwen/Qwen3-VL-235B-A22B-Instruct$0.30/MTok$1.50/MTok262K262K
LLM Gatewaynovita/qwen3-vl-235b-a22b-instruct$0.30/MTok$1.50/MTok131.1K32.8K
NovitaAIqwen/qwen3-vl-235b-a22b-instruct$0.30/MTok$1.50/MTok131.1K32.8K
Heliconeqwen3-vl-235b-a22b-instruct$0.30/MTok$1.50/MTok256K16.4K
Hugging FaceQwen/Qwen3-VL-235B-A22B-Instruct$0.30/MTok$1.50/MTok131.1K32.8K
Jalapeno CloudQwen3-VL-235B-A22B-Instruct$0.30/MTok$1.50/MTok129.0K32.8K
SiliconFlowQwen/Qwen3-VL-235B-A22B-Instruct$0.30/MTok$1.50/MTok262K262K
OrcaRouterqwen/qwen3-vl-235b-a22b-instruct$0.40/MTok$1.60/MTok131.1K32.8K
Vercel AI Gatewayalibaba/qwen3-vl-235b-a22b-instruct$0.40/MTok$1.60/MTok131.1K129.0K
Eden AIqwen/qwen3-vl-235b-a22b-instruct$0.40/MTok$1.60/MTok131.1K32.8K
Amazon Bedrockqwen.qwen3-vl-235b-a22b$0.53/MTok$2.66/MTok262.1K262K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output