AxForge offering · Request
DeepSeek's 3B document model: OCR that turns scanned pages, PDFs and images into text and markdown with tables and layout, under MIT. Validated on AxForge hardware with a dedicated DGX Spark deployment option for your traffic only, subject to confirmed availability, configuration and licence, as an OpenAI-compatible endpoint on hardware only you use, operated by AxForge in the EU.
Currently request-only. Add your request to the public forum; this is not a booking or a promised launch.
Why AxForge
| 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 | For an agreed deployment, subject to availability: 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 |
| Licence | Open weights (mit); commercial use permitted |
| Hardware | NVIDIA DGX Spark (GB10, 128 GB unified memory), owned and operated by AxForge |
| Rental term | Hour, week, month or year |
| Hardware pricing | €1.19/hour on demand · €0.95/hour by the week · €0.91/hour by the month · €0.85/hour by the year |
| Managed service | Quoted per deployment |
| Region | Málaga, Spain (eu-es-1) |
DeepSeek-OCR catalogue reference: specifications and requirements. List prices in EUR.
How it works
| 1 | Add a public request describing your workload, context needs and preferred rental term. A request does not reserve hardware or promise a deployment. |
|---|---|
| 2 | If AxForge can offer a deployment, agree the configuration, hardware rental, licence and managed-service price in writing before anything is billed. |
| 3 | Only after availability and terms are confirmed would AxForge provision the agreed dedicated system and model build. |
| 4 | After provisioning, point your OpenAI SDK at your own endpoint with the model name you receive. |
| 5 | After provisioning, adjust the term (hour, week, month or year) as your workload settles. |
Request model or sign in to start.
FAQ
This page describes the managed deployment option. Availability, the model build, hardware, licence and price must be agreed before a deployment can be offered. A public request does not provision or reserve a machine. Check the console for the current serverless offering list.
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 would set up the page-to-image step with the deployment so you send documents and receive markdown. Any deployment depends on confirmed availability, configuration, licence and price.
AxForge publishes only numbers it measures itself, and has not benchmarked this model on its nodes yet. For quality benchmarks, see the official model card.
For a deployment agreed after availability is confirmed: Hardware by the hour, week, month or year; the managed service is quoted per deployment. Both are confirmed in writing before anything is billed.