DeepSeek-OCR 2
DeepSeek-OCR 2 is DeepSeek's image to text model. An upgraded multimodal document recognition model from DeepSeek AI featuring the DeepEncoder V2 architecture for improved document understanding.
DeepSeek's image to text model. An upgraded multimodal document recognition model from DeepSeek AI featuring the DeepEncoder V2 architecture for improved document understanding.deepseek-ocr-2 |
| Image to Text |
| Active |
| DeepSeek |
| Text |
| Text |
Capabilities
Input1/5
✓
·
·
·
·
Output1/5
✓
·
·
·
·
Capabilities0/13
·
·
·
·
·
·
·
·
·
·
·
·
·
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| DeepSeek-OCR 2 | — | — | — | — | Current |
| DeepSeek-OCR | — | 8K | $0.030 | $0.030 | Available |
| DeepSeek-OCR | — | — | — | — | Available |
| Document OCR | — | — | — | — | Available |
| Mistral OCR | — | — | $2.00 | $3.00 | Available |
| OCR | — | — | — | — | Available |
| Prebuilt Document | — | — | $0.000 | $0.000 | Available |
| Prebuilt Layout | — | — | $0.000 | $0.000 | Available |
| Prebuilt Read | — | — | $0.000 | $0.000 | Available |