Dedicated model · Available as managed deployment
DeepSeek's 3B document model: OCR that turns scanned pages, PDFs and images into text and markdown with tables and layout, under MIT. Available as a managed deployment: validated on AxForge hardware and deployed on a DGX Spark for your traffic only, as an OpenAI-compatible endpoint on hardware only you use, hosted in the EU.
Why DeepSeek-OCR
| Documents in, text out | Scanned pages, forms, invoices and books become clean text and markdown, with tables, headings and reading order preserved. |
|---|---|
| Thousands of pages an hour | A 3B model on a dedicated DGX Spark processes documents at a rate a general vision model cannot match, at a fraction of the cost. |
| Stays in the EU | Contracts, medical records and customer documents never leave your dedicated machine. No third-party OCR API, zero retention. |
Specifications
| Model | DeepSeek-OCR by deepseek-ai |
|---|---|
| Modalities | Text + vision, accepts image input |
| Sizes | 3.3B |
| Context window | 8,192 tokens |
| Released | 2025-10 |
| Popularity | 2.4M downloads / month on HuggingFace |
| Licence | Open weights (MIT); commercial use permitted |
| Availability | Available as managed deployment, operated by AxForge on hardware reserved for you |
| Hardware | NVIDIA DGX Spark (GB10, 128 GB unified memory), owned and operated by AxForge |
| Region | Málaga, Spain (eu-es-1) |
| Pricing | Hardware from €0.85/hour, rental term: Hour, week, month or year. Managed service quoted per deployment. Request deployment and we confirm both in writing. |
We publish only numbers we measure ourselves, and we haven't benchmarked this model on our nodes yet. For quality benchmarks, see the model card in the catalogue and the official card on HuggingFace.
Deployment
| System | A dedicated NVIDIA DGX Spark (GB10, 128 GB unified memory), reserved for you |
|---|---|
| Commercial model | Hour, week, month or year. Hardware from €0.85/hour, managed service quoted per deployment |
| Endpoint | OpenAI-compatible /v1 on your own machine, only your traffic |
| Location | Hosted in the EU: Málaga, Spain (eu-es-1) |
| Data handling | Zero prompt retention, same policy as the serverless API |
The model is validated on AxForge hardware and deployed on your system. After deployment, your endpoint speaks the OpenAI API with the model name you receive with the deployment.
Data & privacy
Prompts and completions are processed in memory in the EU, not written to disk, not logged, not retained, and never used to train anything. We keep only request metadata (token counts, timestamps, status) for billing and operations. The full policy is at axforge.ai/privacy.
FAQ
Not on the serverless API. It is available as a managed deployment: validated on AxForge hardware and deployed on a DGX Spark for your traffic only. The serverless API serves Qwen3.8 27B.
It is built for one job, reading documents into text, and does it faster and cheaper than a general vision model; for questions about the content, pair it with an LLM on the same machine.
Images and page renders of PDFs; AxForge sets up the page-to-image step with the deployment so you send documents and receive markdown.
We publish only numbers we measure ourselves, and we haven't benchmarked this model on our nodes yet. For quality benchmarks, see the official model card.
A dedicated NVIDIA DGX Spark (GB10, 128 GB unified memory) rented by the hour, week, month or year, running DeepSeek-OCR behind an OpenAI-compatible endpoint on your own machine, hosted in the EU with zero prompt retention.
Hardware from €0.85/hour, by the hour, week, month or year; the managed service is quoted per deployment. Request deployment and we confirm both in writing.
Explore