AxForge offering
When this offering is available: Qwen3.8 27B through an OpenAI-compatible endpoint on hardware AxForge owns in Stockholm. Change base_url, use your existing SDK, keep your prompts in the EU, with zero prompt retention.
Check the console for current access, prices and availability.
Why AxForge
| OpenAI-compatible | Chat completions, streaming, tool calls and usage reporting follow the OpenAI API shape. Point your SDK at api.axforge.ai/v1 and pick the model qwen3.8-27b-nvfp4. |
|---|---|
| 262,144-token context | Long documents, large tool outputs and multi-step agent work in one request. |
| Zero prompt retention | Prompts and completions are processed in memory in Stockholm, Sweden. Not logged, not retained, never used for training. |
Specifications
| Model | Qwen3.8 27B: dense 27B, latest Qwen generation |
|---|---|
| API model name | qwen3.8-27b-nvfp4 |
| Context window | 262,144 tokens |
| Quantization | NVFP4 |
| Capabilities | Chat completions · streaming · tool calls · reasoning output · usage in both modes |
| Hardware | NVIDIA DGX Spark (GB10), owned and operated by AxForge |
| Region | Stockholm, Sweden (eu-se-1) |
| Input price | €0.25 / 1M tokens |
| Output price | €1.49 / 1M tokens |
Qwen3.8 27B catalogue reference: specifications and requirements. List prices in EUR.
How it works
| 1 | Confirm this offering is available in the console before following the API setup steps below; otherwise add a public request. A request does not activate an endpoint. |
|---|---|
| 2 | Sign in to AxForge. Your API key is created in the console. |
| 3 | Set base_url to https://api.axforge.ai/v1 in the OpenAI SDK you already use. |
| 4 | Send your first request with model qwen3.8-27b-nvfp4. |
| 5 | Watch usage in the console; every new account starts with free tokens. |
FAQ
Yes. Chat completions, streaming, tool calls and usage reporting follow the OpenAI API shape, so the official SDKs work by changing base_url.
In Stockholm, Sweden (eu-se-1), on NVIDIA DGX Spark systems AxForge owns and operates. TLS terminates in the EU.
When available, check current pricing in the console. Launch pricing is €0.25 per million input tokens and €1.49 per million output tokens. No subscription, no minimum.
No. Prompts and completions are processed in memory and never persisted or used for training.
A dedicated DGX Spark is a deployment option, subject to confirmed capacity, configuration, licence and price. A request does not provision or reserve a machine.