Back to all models
qwen
Qwen: Qwen3 VL 8B Thinking
Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning across complex scenes, documents, and temporal sequences. It integrates enhanced multimodal alignment and...
qwen/qwen3-vl-8b-thinking
Context Size
131.072K
Input Price
719.55 Ks/M
Output Price
8,394.75 Ks/M
Architecture
Image
Text
Supported Parameters
include_reasoningmax_tokenspresence_penaltyreasoningresponse_formatseedstructured_outputstemperaturetool_choicetoolstop_p
Details
TokenizerQwen3
Max Completion32,768 tokens
Provider Context131.072K tokens
ModeratedNo