Title: DeepSeek OCR | LLM EU
Canonical: https://llmeu.com/en/models/deepseek-ocr/
Markdown mirror: https://llmeu.com/en/models/deepseek-ocr.md
Machine-readable: https://llmeu.com/llms.txt (index) - https://llmeu.com/llms-full.txt (full catalogue) - https://llmeu.com/llms-catalogue.json
Provider: DeepSeek
Licence: mit
Hosting: catalogue only %E2%80%94 not hosted on LLM EU yet
Sources: https://huggingface.co/deepseek-ai/DeepSeek-OCR https://huggingface.co/api/models/deepseek-ai/DeepSeek-OCR?blobs=true https://opensource.org/license/mit

# DeepSeek OCR

[DeepSeek](/en/providers/deepseek/)

Last reviewed: 14 Oct 2026

## Sovereignty and hosting

This model is catalogued for reference. It is not hosted on LLM EU yet, and no first-party endpoint serves it here. Requests to it go to the provider directly, under that provider's own terms.

## Summary

DeepSeek OCR is an open-weight vision-language model from DeepSeek with 3.3B parameters, published under MIT. It accepts text and images and answers in text. The published configuration records no context window, so this card carries none. It is a base checkpoint without instruction tuning. The card is catalogue-only: LLM EU does not run this model. The publisher lists 1 language.

## Specifications

- Provider
  DeepSeek (CN)
- Context window
  Not verified: the provider has not documented this claim.
- Parameters
  3.3B
- Modalities
  text, vision
- License
  mit %C2%B7 [licence](https://opensource.org/license/mit)
- Open weights
  yes
- Release date
  17 Oct 2025
- Tasks
  [Vision](/en/tasks/vision/), [Retrieval (RAG)](/en/tasks/rag/), [Low cost](/en/tasks/cheap/)

## Languages

**Strong:** %E2%80%94

**Adequate:** ocr

#### Strong

#### Adequate

- ocr

Not verified: the provider has not documented this claim. %E2%80%94 a language is listed as strong only where a source claims it; the card links the evidence where one exists.

## When to use it

#### Strengths

- open weights are published on Hugging Face and can be downloaded without a vendor agreement
- mit licence, so commercial self-hosting is permitted without a separate agreement
- at 3.3B parameters it fits on a single accelerator

#### Limits

- catalogue only %E2%80%94 LLM EU does not run this model, and nothing on this card implies an LLM EU endpoint
- no evaluation has been run by LLM EU
- the published configuration records no context window, so the card carries none
- at 3.3B parameters, the weights fit on a single modest accelerator
- vision checkpoints are heavier to serve than their parameter count alone suggests, because the image encoder and pre-processing run alongside the language model

### Pricing

This model is catalogued for reference. It is not hosted on LLM EU yet, and no first-party endpoint serves it here. Requests to it go to the provider directly, under that provider's own terms.

### Verification status

Where a field has no source, the card shows it as unverified instead of filling it in. An empty field is information.

LLM EU Verified means documented, not legally certified. It is not an AI Act conformity assessment and LLM EU is not an EU body.

### Versions and variants

- catalogue %C2%B7 Catalogue only %C2%B7 [weights](https://huggingface.co/deepseek-ai/DeepSeek-OCR)

### Example request

```
curl https://api.llmeu.com/v1/chat/completions \
  -H "Authorization: Bearer $LLMEU_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek-ocr","messages":[{"role":"user","content":"Hello"}]}'
```

No playground is deployed for this model: no endpoint serves it, so a request would have nowhere to go.

### Benchmarks

No published evaluation. This is a gap, not a hidden result.

### Sources

- [huggingface.co](https://huggingface.co/deepseek-ai/DeepSeek-OCR)
- [huggingface.co](https://huggingface.co/api/models/deepseek-ai/DeepSeek-OCR?blobs=true)
- [opensource.org](https://opensource.org/license/mit)

### Card changelog

- 17 Oct 2025 %E2%80%94 Release date
- 14 Oct 2026 %E2%80%94 Last reviewed

Last reviewed: 14 Oct 2026