DeepSeek
DeepSeek OCR 2
High-accuracy OCR model for extracting text from documents, screenshots, receipts, and natural scenes
Model facts
- Context window
- 8K tokens
- Maximum output
- 8K tokens
- Cheapest paid input
- $0.03 per 1M tokens
- Cheapest paid output
- $0.03 per 1M tokens
- Open weights
- yes
- Providers
- 3
Capabilities and modalities
attachments, open weights, text, image.
Local hardware estimate
At 4K context: Q4_K_M 3.1 GiB, Q8_0 4.6 GiB, F16 7.6 GiB working memory.
- Parameters
- 3.4 billion
- Architecture
- deepseekocr2
- Model license
- apache-2.0
Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.
Observed price history
- 2026-08-24: $0.03 input / $0.03 output per 1M tokens
API providers
- Regolo AI — model id deepseek-ocr-2; free input / free output per 1M tokens; provider documentation
- NovitaAI — model id deepseek/deepseek-ocr-2; $0.03 input / $0.03 output per 1M tokens; provider documentation
- Privatemode AI — model id deepseek-ocr-2; $0.89 input / $1.47 output per 1M tokens; provider documentation