DeepSeek OCR is a specialized optical character recognition model, available free on SiliconFlow's API.
https://api.siliconflow.cn/v1 deepseek-ai-deepseek-ocr DeepSeek-OCR is listed for chat workloads and supports a 131K context window.
Check SiliconFlow's current endpoint status before integrating this listing. Use the alternatives table if the provider listing is unavailable.
We only found this DeepSeek-OCR listing on SiliconFlow in the current catalog. Use the related models section for nearby alternatives.
| Provider | Model listing | Access | Context | API | Limits |
|---|---|---|---|---|---|
| | deepseek-ai/DeepSeek-OCR | Check provider | 131K | OpenAI-style | 30 RPM, 60K TPM |
| Model | Provider | Context | Access |
|---|---|---|---|
| deepseek-ai/DeepSeek-R1-Distill-Qwen-7B | SiliconFlow | 131K | Free tier |
| Abbreviation | SiliconFlow | 131K | Free tier |
DeepSeek-OCR is tagged for chat in this catalog and works with OpenAI-compatible client libraries.
DeepSeek-OCR appears in the free model catalog for SiliconFlow, but its current endpoint availability should be confirmed with the provider before use.
The model ID shown in this catalog is deepseek-ai-deepseek-ocr.
The listed free tier limit is 30 RPM, 60K TPM. Limits can change per account tier, so confirm against the provider dashboard.
The listed context window is 131K tokens with up to 8K output tokens.
DeepSeek OCR is a specialized optical character recognition model, available free on SiliconFlow's API. Unlike general-purpose models, it is optimized specifically for extracting text from images, documents, and screenshots. OpenAI-compatible endpoint. Ideal for document digitization pipelines and data extraction workflows. Free tier requires registration.
For API keys, setup steps, and provider-level limits, see the SiliconFlow provider page.