DeepSeek VL 7B

DeepSeek-VL 7B is an open-source vision-language model engineered for robust real-world applications. With its general multimodal understanding capabilities, it can process logical diagrams, web pages, formulas, scientific literature, natural images, and complex scenarios involving embodied intelligence. The model features a hybrid vision encoder that integrates SigLIP-L and SAM-B, allowing it to handle high-resolution (1024 x 1024) image inputs. Built on the DeepSeek-LLM-7b-base foundation, it is pre-trained on roughly 2 trillion text tokens and further trained on approximately 400 billion vision-language tokens. A standout variant, DeepSeek-VL-7b-chat, is specially optimized for conversational tasks, enhancing both performance and user experience by addressing the limitations of existing open-source multimodal models.

DeepSeek VL 7B is an open-weight model in the DeepSeek VL family. The structured metadata tracks multimodal input. This page tracks provider routes through Replicate API, with the cheapest tracked route listed at $0.05 input and $0.25 output per 1M tokens. No headline benchmark score is tracked for DeepSeek VL 7B yet.