DeepSeek-OCR 2
DeepSeek-OCR 2 is DeepSeek's image to text model with a 8K context window and up to 8K output tokens, starting at $0.03 / 1M input and $0.03 / 1M output. An upgraded multimodal document recognition model from DeepSeek AI featuring the DeepEncoder V2 architecture for improved document understanding.
| Specifications | |
|---|---|
deepseek-ocr-2 | |
| Image to Text | |
| Active | |
| DeepSeek | |
| 8K tokens | |
| 8K tokens | |
| ImageText | |
| Text | |
Capabilities
Input2/5
Text✓
Image✓
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | |
|---|---|---|
| Input $ / 1M | Output $ / 1M | |
| $0.03 | $0.03 | |
Cost Calculator
US Dollar ($)
Preset:
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Mistral OCR 4 | — | — | — | — | Available |
| Mistral OCR 4 Annot | — | — | — | — | Available |
| DeepSeek-OCR 2 | — | 8K | $0.030 | $0.030 | Current |
| LightOn OCR 2 1B | — | — | — | — | Available |
| Qianfan OCR Fast | 66K | — | — | Deprecated | |
| DeepSeek-OCR | — | — | — | — | Available |
| Document OCR | — | — | — | — | Available |
| Mistral OCR | — | — | — | — | Deprecated |
| OCR | — | — | — | — | Available |
| Prebuilt Document | — | — | — | — | Available |
| Prebuilt Layout | — | — | — | — | Available |