Dedicated model · Available as managed deployment
DeepSeek's reasoning model: a 671B mixture-of-experts trained with reinforcement learning to think before it answers, with a 164k-token context, under MIT. Available as a managed deployment: validated on AxForge hardware and deployed on a multi-GPU system for your traffic only, as an OpenAI-compatible endpoint on hardware only you use, hosted in the EU.
Why DeepSeek-R1
| Reasoning at the top of the open field | R1 made long-form chain-of-thought reasoning available as open weights, for maths, code, analysis and planning tasks where a step-by-step model wins. |
|---|---|
| MIT licence | The most permissive licence in the field: no usage conditions, distillation allowed, commercial use allowed. |
| Your own R1, in the EU | A multi-GPU system reserved for you, with prompts processed in memory and never retained, so the reasoning stays in Europe. |
Specifications
| Model | DeepSeek-R1 by deepseek-ai |
|---|---|
| Modalities | Text |
| Sizes | 684.5B |
| Context window | 163,840 tokens |
| Released | 2025-01 |
| Popularity | 2.2M 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 | Multi-GPU system (H100, H200 or B200 class) sourced against your request |
| Region | European region, placement confirmed with your request |
| Pricing | Hardware and 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 multi-GPU system reserved for you, sized to the model and your traffic |
|---|---|
| Commercial model | Hardware and 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 multi-GPU system for your traffic only. The serverless API serves Qwen3.8 27B.
A multi-GPU system (H100, H200 or B200 class), which AxForge sources against your request and confirms in writing before anything is billed.
Yes, the R1 distilled models (Qwen and Llama based, 1.5B to 70B) carry much of the reasoning behaviour and fit a single dedicated machine; ask for them in the request.
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 multi-GPU system reserved for you, running DeepSeek-R1 behind an OpenAI-compatible endpoint, hosted in the EU with zero prompt retention.
Hardware and the managed service are Quoted per deployment. Request deployment and we confirm both in writing.
Explore