DeepSeek OCR 2 API
About
Integrate multimodal vision capabilities using DeepSeek OCR 2, designed to process both text and images seamlessly. This model delivers available completely free of charge, open weights architecture. Access DeepSeek OCR 2 via the Regolo AI API with up to 4K output tokens.
Capabilities
Input Modalities
textimage
Output Modalities
text
Reasoning
No
Structured Output
No
Tool Use
No
WeightsOpen
Temperature
Fixed
Attachment
Supported
Limits
Context Window
4K
Tokens
Input Limit
4K
Tokens
Max Output
4K
Tokens
Pricing
Standard (per 1M tokens)
Input
Free
Output
Free
Frequently Asked Questions
DeepSeek OCR 2 by Regolo AI costs Free per 1M input tokens and Free per 1M output tokens.
Model Details
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
REGOLO_API_KEY
API Base URL
https://api.regolo.ai/v1