Model API · served now

Qwen3.8 27B API — hosted in Europe

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.

eu-se-1 · Stockholm api.axforge.ai/v1 €0.29 / 1M input · €1.77 / 1M output No subscription · no minimum
Get an API key View quickstart Talk to an engineer Launch pricing, excluding VAT. Self-serve signup is open — create an account and get an API key in minutes.

Quickstart

OpenAI-compatible — point your SDK at us

Keep the OpenAI client you already use: change base_url, set your AxForge key and pick the model qwen3.8-27b-nvfp4. Streaming, tool calls and usage reporting follow the OpenAI API shape.

curl
$ export OPENAI_BASE_URL=https://api.axforge.ai/v1
$ curl -sS "$OPENAI_BASE_URL/chat/completions" \
    -H "Authorization: Bearer $AXFORGE_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{"model":"qwen3.8-27b-nvfp4","stream":true,
         "messages":[{"role":"user","content":"Summarize DORA in one paragraph."}]}'
Python
# pip install openai
from openai import OpenAI

client = OpenAI(
    base_url="https://api.axforge.ai/v1",
    api_key="YOUR_AXFORGE_KEY",
)
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)

Specifications

What is served

ModelQwen3.8 27B — dense 27B, latest Qwen generation
API model nameqwen3.8-27b-nvfp4
Context window131,072 tokens
QuantizationNVFP4
CapabilitiesChat completions · streaming · tool calls · reasoning output · usage in both modes
HardwareNVIDIA DGX Spark (GB10, 128 GB unified memory) — owned and operated by AxForge
Regioneu-se-1 · Stockholm, Sweden — inference stays in-region
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

Community benchmark — labelled, not ours

MetricValueCondition
Decode speed (community)25.1 tokens/sSparkBench PBM @ 4k context, single GB10, NVFP4 + MTP
Concurrency4 sequencesour serving configuration on one node

Community measurement from SparkBench for this model on the same hardware class — we haven't published our own tuned numbers yet. More community data on the GB10 page; for quality benchmarks, see the official model card.

Fit

What developers build on it

Use caseWhy it fits
Private assistants & copilotsInternal or customer-facing assistants with prompts and completions processed in the EU.
Tool-using agentsOpenAI-compatible tool calls connect the model to your applications, workflows and data.
Long-context analysisUp to 131,072 tokens for document analysis, synthesis and multi-step tasks.
Streaming applicationsTokens stream as they are generated — responsive chat and interactive products.
Development & evaluationA transparent model name, pinned region and usage reporting — prototype before moving to dedicated capacity.
EU-hosted inference requirementsInference runs on hardware AxForge owns and operates in Sweden; TLS terminates in the EU.

Data & privacy

Zero prompt retention on the API

This describes the customer /v1 API: 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.

Scale up

From API to your own machine

Start with the Qwen API — no subscription, no minimum. When you need isolated capacity or control over the machine itself, move to a dedicated NVIDIA DGX Spark for €495/month: the same hardware the API runs on, single-tenant, in the same Stockholm region. Nothing forces the move — the API scales on its own.

FAQ

Qwen3.8 27B API — common questions

Is the Qwen3.8 API OpenAI-compatible?

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.

Where is Qwen3.8 hosted?

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.

What does the Qwen3.8 27B API cost?

Launch pricing is €0.29 per million input tokens and €1.77 per million output tokens, excluding VAT. No subscription, no minimum.

What is the context window?

131,072 tokens in the production serving configuration — enough for long documents, large tool outputs and multi-step agent work in a single request.

Are my prompts stored or used for training?

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.

How fast is Qwen3.8 27B on your hardware?

On the community SparkBench leaderboard (PBM methodology, 4k context, single GB10), Qwen3.8-27B with NVFP4 + MTP measures 25.1 tokens/s single-stream. We haven't published our own tuned numbers yet.

Can I get Qwen3.8 on a dedicated machine instead of the serverless API?

Yes — a dedicated DGX Spark running Qwen3.8 27B for only your traffic is €495/month on monthly rental. Talk to an engineer to scope it.

Ready to build on EU inference?

Get an API key Talk to an engineer

Explore

All models

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms