Model API · served now
Qwen3.8 27B through an OpenAI-compatible API, served from hardware AxForge owns in Sweden. Streaming, tool calls and usage reporting — with zero prompt retention.
Specifications
| Model | Qwen3.8 27B — dense 27B, latest Qwen generation |
|---|---|
| API model name | qwen3.8-27b-nvfp4 |
| Context window | 65,536 tokens |
| Quantization | NVFP4 |
| Capabilities | Chat completions · streaming · tool calls · reasoning output · usage in both modes |
| Hardware | NVIDIA DGX Spark (GB10, 128 GB unified memory) — owned and operated by AxForge |
| Region | eu-se-1 · Stockholm, Sweden — pinned with x-axforge-region, echoed on the response |
| Input price | €0.29 / 1M tokens |
| Output price | €1.77 / 1M tokens |
Our pricing rule: we target 80% of the lowest current price from a proper inference supplier for the same model, tracked continuously against the market. Found better pricing at a proper inference supplier? Tell us and we’ll look into lowering ours.
Performance
| Metric | Value | Condition |
|---|---|---|
| Decode speed | 15.9 tokens/s | single stream, multi-token-prediction speculative decoding on |
| Decode speed (baseline) | 5.8 tokens/s | single stream, speculative decoding off |
| Concurrency | 4 sequences | serving configuration on one node |
Measured on our production DGX Spark node, single-stream, 2026-08. For quality benchmarks, see the official model card — we publish only numbers we measured ourselves.
Quickstart
$ export OPENAI_BASE_URL=https://api.axforge.ai/v1 $ curl -sS "$OPENAI_BASE_URL/chat/completions" \ -H "Authorization: Bearer $AXFORGE_API_KEY" \ -H "x-axforge-region: eu-se-1" \ -H "Content-Type: application/json" \ -d '{"model":"qwen3.8-27b-nvfp4","stream":true, "messages":[{"role":"user","content":"Summarize DORA in one paragraph."}]}'
# pip install openai from openai import OpenAI client = OpenAI( base_url="https://api.axforge.ai/v1", api_key="YOUR_AXFORGE_KEY", default_headers={"x-axforge-region": "eu-se-1"}, ) r = client.chat.completions.create( model="qwen3.8-27b-nvfp4", messages=[{"role": "user", "content": "Hello from Stockholm"}], ) print(r.choices[0].message.content, r.usage)
Data & privacy
Prompts and completions are processed in memory in Sweden — 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
Yes. Chat completions, streaming, tool calls and usage reporting follow the
OpenAI API shape, so the official OpenAI SDKs work by changing
base_url. The model name is qwen3.8-27b-nvfp4.
In Stockholm, Sweden (region eu-se-1), on NVIDIA DGX Spark
systems AxForge owns and operates. TLS terminates in the EU. Spain
(eu-es-1) is live for the platform; more EU regions are in
deployment.
Launch pricing is €0.29 per million input tokens and €1.77 per million output tokens. No subscription, no minimum.
No. Prompts and completions are processed in memory and never persisted or used for training — see the privacy policy. This makes the API a fit for GDPR-sensitive workloads.
We measured 15.9 tokens/s single-stream decode with speculative decoding on our production DGX Spark node (2026-08). We publish measured numbers only.
Yes — a dedicated DGX Spark running Qwen3.8 27B for only your traffic is a monthly rental. Talk to an engineer.