← All models
DeepSeek OCR
deepseek-ai/
Deepseek Ai model · Served by DeepInfra · live on the gateway · :free available
Input / 1M
$0.030
Output / 1M
$0.100
Context
8K tokens
Max output
8K tokens
Input
Text, Image
Released
12mo ago
Pricing
Input tokens$0.030 per 1M
Output tokens$0.100 per 1M
Provider list priceExactly what your balance is debited; our fee is charged when you buy credits
About DeepSeek OCR
OCR model for extracting structured text from documents and screenshots
Vision
What it supports
- Tool calling (function calling)
- JSON mode and structured output
- Image input (vision)
- Audio input
- Extended reasoning
- Streaming responses
- OpenAI SDK, Anthropic SDK and any OpenAI-compatible client
Make a request
curl https://rapidrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $RAPIDROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-ai/deepseek-ocr",
"messages": [{ "role": "user", "content": "Hello" }]
}'Frequently asked
How do I call DeepSeek OCR through an OpenAI-compatible API?
Point any OpenAI-compatible client at https://rapidrouter.ai/api/v1 with a Rapid Router API key and set the model to deepseek-ai/deepseek-ocr. The chat completions endpoint is https://rapidrouter.ai/api/v1/chat/completions.
What is the context window of DeepSeek OCR?
DeepSeek OCR has a context window of 8,192 tokens on Rapid Router, and returns up to 8,192 output tokens per reply.
Is there a free version of DeepSeek OCR?
Yes. Call deepseek-ai/deepseek-ocr:free and the request is paid for from Rapid Router's sponsored daily pool, within the free tier's daily request limit.
What can DeepSeek OCR do?
On Rapid Router, DeepSeek OCR supports image input.
More Deepseek Ai models
DeepSeek Prover V2 671B$0.500/M in · $2.18/M outDeepSeek R1 0528 Turbo$1.00/M in · $3.00/M outDeepSeek R1 Distill Qwen 32B$0.270/M in · $0.270/M outDeepSeek R1 Distill Qwen 32B (free)Free/M in · Free/M outDeepSeek R1 (Turbo)$1.00/M in · $3.00/M outDeepSeek V3$0.320/M in · $0.890/M outEvery Deepseek Ai model, priced →