AI Model Radar / AI模型雷达

DeepSeek VL2

Model detail, capability tags, source, OpenRouter state, and public reputation.

Model detail

DeepSeek VL2

DeepSeek's current public VL2 multimodal understanding family.

multimodalvision_languagechatdocument_understandinglocal_inference
Current version

deepseek-vl2

CompanyDeepSeek
ReleaseNot disclosed
ContextNot disclosed
Parameters27B
Input modalitiestext / image
Output modalitiestext
Tool use / Function callingNo reliable public source / No reliable public source
Structured output / ReasoningNo reliable public source / No reliable public source
Vision / Audio / VideoYes / No / No
Open weights / LicenseYes / DeepSeek Model License
OpenRouterNo reliable public source
Community reputation1 public signals
Versions
officialdeepseek-vl2
deepseek-vl2-current · activeP0