DeepSeek OCR

OCR

deepseek-ocr · DeepSeek · text

Back to Models Back to Docs

Platform

DeepSeek

Visit Official Site

API Pricing

Input / 1M

$0.05/M

Output / 1M

$0/M

Overview

DeepSeek OCR — Model integration guide (deepseek).

Capabilities

Input: text. Output: text. Context window: 32768 tokens. Maximum output: 8192 tokens.

Use Cases

Choose conversation, generation, retrieval or media workflows that match the input and output modalities.

Limitations

Catalog registration does not grant model access. Check channel routing, account permissions, quotas and API compatibility before production use. Official reference: https://api-docs.deepseek.com/quick_start/pricing

Examples

Claude Code

Anthropic official CLI coding agent. Multi-file edits, tool use, long-context reasoning.

Terminal

export ANTHROPIC_AUTH_TOKEN="YOUR_API_KEY"
export ANTHROPIC_BASE_URL="https://api.robovai.com"
export ANTHROPIC_MODEL="deepseek-ocr"
claude

Context Window

33K ctx

Thinking Mode

Not supported

Overview

DeepSeek OCR, a document understanding model that extracts text and structure from images and scanned documents.