Integrate multimodal vision capabilities using deepseek-ai/DeepSeek-OCR, designed to process both text and images seamlessly. This model delivers available completely free of charge, open weights architecture. Access deepseek-ai/DeepSeek-OCR via the SiliconFlow (China) API with up to 8K output tokens.
Tokens
Tokens
Tokens
deepseek-ai/DeepSeek-OCR by SiliconFlow (China) costs Free per 1M input tokens and Free per 1M output tokens.