Model reference · open weights
DeepSeek-OCR-2 is an open-weight language model from deepseek-community. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Released by | deepseek-community |
|---|---|
| Type | Language models |
| Task | Vision + text |
| Parameters (lead) | 3.4B |
| Context | 8k tokens |
| Runs with | transformers |
| Released | 2026-05-27 |
| Popularity | 47k downloads / month |
| Licence | Open weights |
About
from transformers import AutoProcessor, AutoModelForImageTextToText
model = AutoModelForImageTextToText.from_pretrained(
"deepseek-community/DeepSeek-OCR-2", device_map="auto"
)
processor = AutoProcessor.from_pretrained("deepseek-community/DeepSeek-OCR-2")
image = "https://huggingface.co/datasets/hf-internal-testing/fixtures_got_ocr/resolve/main/image_ocr.jpg"
inputs = processor(images=image, text="\nFree OCR.", return_tensors="pt").to(model.device)
generate_ids = model.generate(**inputs, do_sample=False, max_new_tokens=256)
print(processor.decode(generate_ids[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True))
# "R&D QUALITY IMPROVEMENT\nSUGGESTION/SOLUTION FORM\nName/Phone Ext. : (...)"
The token enables coordinate-aware output with and `` tags.
inputs = processor(
images=image,
text="\nConvert the document to markdown.",
return_tensors="pt",
).to(model.device)
generate_ids = model.generate(**inputs, do_sample=False, max_new_tokens=256)
print(processor.decode(generate_ids[0, inputs["input_ids"].shape[1]:], skip_special_tokens=False))
# "title[[330, 198, 558, 230]]\n# R&D QUALITY (...)"
Refer to 🌟GitHub for guidance on model inference acceleration and PDF processing.
# document: "\nConvert the document to markdown."
# without layouts: "\nFree OCR."
We would like to thank DeepSeek-OCR, Vary, GOT-OCR2.0, MinerU, PaddleOCR for their valuable models and ideas.
We also appreciate the benchmark OmniDocBench.
@article{wei2025deepseek,
title={DeepSeek-OCR: Contexts Optical Compression},
author={Wei, Haoran and Sun, Yaofeng and Li, Yukun},
journal={arXiv preprint arXiv:2510.18234},
year={2025}
}
@article{wei2026deepseek,
title={DeepSeek-OCR 2: Visual Causal Flow},
author={Wei, Haoran and Sun, Yaofeng and Li, Yukun},
journal={arXiv preprint arXiv:2601.20552},
year={2026}
}
From the published model card. Full card on the HuggingFace links in the sidebar.
Using it via the API
Once AxForge deploys deepseek-community-deepseek-ocr-2 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (deepseek-community-deepseek-ocr-2 below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"deepseek-community-deepseek-ocr-2","messages":[{"role":"user","content":"Hello"}]}'
Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.