Dedicated model · Available as managed deployment
OpenAI's open-weight reasoning models (20B and 120B mixture-of-experts), built for agentic work, tool use and long chains of reasoning, under Apache-2.0. 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 gpt-oss
| OpenAI, open weights | The first open-weight models from OpenAI: two sizes, both released under Apache-2.0, with configurable reasoning effort and native tool calling. |
|---|---|
| 20B on one machine | gpt-oss-20b is sized for a single accelerator; on a dedicated DGX Spark it runs as your own OpenAI-compatible endpoint. The 120B build is a multi-GPU deployment. |
| Agents, not just chat | Structured outputs, function calling and a reasoning mode you can dial down for latency: the pieces an agent workflow needs, on hardware only you use. |
Specifications
| Model | gpt-oss by openai |
|---|---|
| Modalities | Text |
| Sizes | 20.9B, 116.8B |
| Released | 2025-08 |
| Popularity | 6.5M downloads / month on HuggingFace |
| Licence | Open weights (Apache 2.0); 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.
gpt-oss-20b for a single dedicated machine and low latency; gpt-oss-120b when quality on hard reasoning matters more than cost. It needs a multi-GPU system, which AxForge scopes with you.
Yes, function calling and structured outputs are part of the model, and they work through the OpenAI-compatible endpoint on your machine.
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 gpt-oss 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