Marketplace · Text & chat
deepseek-ocr:latest
Call deepseek-ocr:latest through one OpenAI-compatible API. It's served by 1 host on the Inpherio grid, each at a price it sets — your request goes to the cheapest healthy one, and fails over to the next if it's down.
At a glance.
vision ocr
from openai import OpenAI
client = OpenAI(base_url="https://inpherio.co.uk/v1",
api_key=INPHERIO_API_KEY)
reply = client.chat.completions.create(
model="deepseek-ocr:latest",
messages=[{"role": "user", "content": "Hello"}],
)deepseek-ocr:latest in detail.
DeepSeek-OCR is a vision-language model that can perform token-efficient OCR.
- Published by
- deepseek-ai
- Parameters
- 3.3B
- Download size
- 6.7 GB (as packaged for Ollama)
- Quantisation
- F16
- Format
- gguf
- Architecture
- deepseek_vl_v2
- Licence
- MIT
- Task
- image text to text
- Library
- transformers
- Languages
- multilingual
- First published
- 17 Oct 2025
- Last updated
- 4 Nov 2025
- Downloads (30 days)
- 2 million on Hugging Face
- Likes
- 3,464
deepseek_vl_v2 feature-extraction deepseek vision-language ocr image-text-to-text multilingual
The model card
Published by the model's authors on Hugging Face — shown as they wrote it, unedited by Inpherio.
🌟 Github | 📥 Model Download | 📄 Paper Link | 📄 Arxiv Paper Link |
DeepSeek-OCR: Contexts Optical Compression
Explore the boundaries of visual-text compression.
Usage
Inference using Huggingface transformers on NVIDIA GPUs. Requirements tested on python 3.12.9 + CUDA11.8:
torch==2.6.0
transformers==4.46.3
tokenizers==0.20.3
einops
addict
easydict
pip install flash-attn==2.7.3 --no-build-isolation
from transformers import AutoModel, AutoTokenizer
import torch
import os
os.environ["CUDA_VISIBLE_DEVICES"] = '0'
model_name = 'deepseek-ai/DeepSeek-OCR'
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModel.from_pretrained(model_name, _attn_implementation='flash_attention_2', trust_remote_code=True, use_safetensors=True)
model = model.eval().cuda().to(torch.bfloat16)
### prompt = "\nFree OCR. "
prompt = "\n<|grounding|>Convert the document to markdown. "
image_file = 'your_image.jpg'
output_path = 'your/output/dir'
### infer(self, tokenizer, prompt='', image_file='', output_path = ' ', base_size = 1024, image_size = 640, crop_mode = True, test_compress = False, save_results = False):
### Tiny: base_size = 512, image_size = 512, crop_mode = False
### Small: base_size = 640, image_size = 640, crop_mode = False
### Base: base_size = 1024, image_size = 1024, crop_mode = False
### Large: base_size = 1280, image_size = 1280, crop_mode = False
### Gundam: base_size = 1024, image_size = 640, crop_mode = True
res = model.infer(tokenizer, prompt=prompt, image_file=image_file, output_path = output_path, base_size = 1024, image_size = 640, crop_mode=True, save_results = True, test_compress = True)
vLLM
Refer to 🌟GitHub for guidance on model inference acceleration and PDF processing, etc.
[2025/10/23] 🚀🚀🚀 DeepSeek-OCR is now officially supported in upstream vLLM.
uv venv
source .venv/bin/activate
### Until v0.11.1 release, you need to install vLLM from nightly build
uv pip install -U vllm --pre --extra-index-url https://wheels.vllm.ai/nightly
from vllm import LLM, SamplingParams
from vllm.model_executor.models.deepseek_ocr import NGramPerReqLogitsProcessor
from PIL import Image
### Create model instance
llm = LLM(
model="deepseek-ai/DeepSeek-OCR",
enable_prefix_caching=False,
mm_processor_cache_gb=0,
logits_processors=[NGramPerReqLogitsProcessor]
)
### Prepare batched input with your image file
image_1 = Image.open("path/to/your/image_1.png").convert("RGB")
image_2 = Image.open("path/to/your/image_2.png").convert("RGB")
prompt = "\nFree OCR."
model_input = [
{
"prompt": prompt,
"multi_modal_data": {"image": image_1}
},
{
"prompt": prompt,
"multi_modal_data": {"image": image_2}
}
]
sampling_param = SamplingParams(
temperature=0.0,
max_tokens=8192,
# ngram logit processor args
extra_args=dict(
ngram_size=30,
window_size=90,
whitelist_token_ids={128821, 128822}, # whitelist: ,
),
skip_special_tokens=False,
)
### Generate output
model_outputs = llm.generate(model_input, sampling_param)
### Print output
for output in model_outputs:
print(output.outputs[0].text)
Visualizations
Acknowledgement
We would like to thank Vary, GOT-OCR2.0, MinerU, PaddleOCR, OneChart, Slow Perception for their valuable models and ideas.
We also appreciate the benchmarks: Fox, OminiDocBench.
Citation
@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}
}Sources: deepseek-ai/DeepSeek-OCR on Hugging Face · deepseek-ocr:latest on Ollama. Collected from public sources on 8 Nov 2026; the host serving it may run a different build or quantisation — the marketplace shows each host's own measurements.
Who's serving it.
Every host benchmarked this model on its own hardware before serving it. Prices are set by each host; health is scored by the platform from what it observes.
| Host | Tier | Price | Measured speed | Health | State | Rent |
|---|---|---|---|---|---|---|
| GTX 1080 Ti (11G) | L1 | £0.058 in · £0.12 out | 19 tok/s · 57 ms first token | 78 | loads on request | £0.60/h |
Live data, refreshed on every visit. How billing works.
Room on the grid for your machine.
Right now one machine serves deepseek-ocr:latest. If it drops, so does every request for it — a second host is what turns it into failover, and the grid needs that more than another copy. The router weighs price, measured speed, health and whether the model is already loaded — so a host with a sharper price or quicker hardware wins the next call.
Set your own price — you keep 85% of what it earns, and new hosts start with 12 months fee-free (up to £250 of earnings). A payout fee of £2 + 1% per payout to a UK bank account, £2 + 2% to any other country applies when you're paid. Install the connector, load deepseek-ocr:latest, and the platform benchmarks it on your hardware before your first request.