DeepSeek-OCR
DeepSeek-OCR is DeepSeek's image to text model. A multimodal vision-language OCR model from DeepSeek AI designed for image-to-text document recognition tasks.
deepseek-ocr-vlm |
| Image to Text |
| Active |
| DeepSeek |
| Text |
| Text |
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| DeepSeek-OCR 2 | — | — | — | — | Available |
| Qianfan OCR Fast | 66K | $0.680 | $2.81 | Deprecating | |
| DeepSeek-OCR | — | — | — | — | Current |
| DeepSeek-OCR | — | 8K | $0.030 | $0.030 | Available |
| Document OCR | — | — | — | — | Available |
| Mistral OCR | — | — | $2.00 | $3.00 | Available |
| OCR | — | — | — | — | Available |
| Prebuilt Document | — | — | — | — | Available |
| Prebuilt Layout | — | — | — | — | Available |
| Prebuilt Read | — | — | — | — | Available |