All Models

Qwen/Qwen3-VL-8B-Instruct

qwen Tool Calling Attachments Open Weights Structured Output

Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon...

Providers 4
Released Oct 15, 2025
Input Modalities text, image, video
Output Modalities text
Tarsk Use coding

Benchmarks

14.3
Intelligence Index
7.3
Coding Index
27.3
Math Index

Available Providers (4)

Provider Model ID Input Cost Output Cost Context Max Output Docs
NovitaAI qwen/qwen3-vl-8b-instruct $0.08/MTok $0.50/MTok 131.1K 32.8K
Kilo Gateway qwen/qwen3-vl-8b-instruct $0.08/MTok $0.50/MTok 131.1K 32.8K
SiliconFlow (China) Qwen/Qwen3-VL-8B-Instruct $0.18/MTok $0.68/MTok 262K 262K
SiliconFlow Qwen/Qwen3-VL-8B-Instruct $0.18/MTok $0.68/MTok 262K 262K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output