Dedicated model · Available as managed deployment
The fast, lighter member of DeepSeek's V4 line, a 291B mixture-of-experts with a 1M-token context, strong on general and coding tasks, 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-V4-Flash
| V4 quality at lower cost | The same generation as V4-Pro with a smaller footprint, the practical choice for high-volume general and coding traffic. |
|---|---|
| 1M-token context | Long documents and long agent runs in one request. |
| MIT licence, EU hardware | No usage conditions; deployed on a system reserved for you in Europe with zero prompt retention. |
Specifications
| Model | DeepSeek-V4-Flash by deepseek-ai |
|---|---|
| Modalities | Text |
| Sizes | 290.9B |
| Context window | 1,048,576 tokens |
| Released | 2026-04 |
| Popularity | 1.7M 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 sourced against your request, smaller than V4-Pro needs; configuration and price are confirmed in writing before anything is billed.
Flash for throughput and cost, Pro for the hardest reasoning and coding tasks. AxForge scopes either with you.
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-V4-Flash 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