All Models

Qwen3 VL 8B Instruct

qwenTool CallingAttachmentsOpen WeightsStructured Output

Qwen vision-language model for visual reasoning, documents, and agent tasks

Providers5
ReleasedOct 14, 2025
Input Modalitiestext, image, video
Output Modalitiestext
Tarsk Usecoding

Benchmarks

7.3
Intelligence Index
27.3
Math Index

Available Providers (5)

ProviderModel IDInput CostOutput CostContextMax OutputDocs
NovitaAIqwen/qwen3-vl-8b-instruct$0.08/MTok$0.50/MTok131.1K32.8K
Kilo Gatewayqwen/qwen3-vl-8b-instruct$0.12/MTok$0.46/MTok131.1K32.8K
OpenRouterqwen/qwen3-vl-8b-instruct$0.12/MTok$0.46/MTok262.1K32.8K
SiliconFlow (China)Qwen/Qwen3-VL-8B-Instruct$0.18/MTok$0.68/MTok262K262K
SiliconFlowQwen/Qwen3-VL-8B-Instruct$0.18/MTok$0.68/MTok262K262K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output