Model API · Available

Qwen3.8 27B API 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 €0.32 / 1M input · €2.00 / 1M output No subscription · no minimum qwen-3-8-27b.axforge.ai
Use Qwen3.8 27B View quickstart Talk to an engineer Create an account and your key is in the console. 3M free tokens every 30 days with every new account. Launch pricing.

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.

# your API key, from API Keys
export AXFORGE_API_KEY="YOUR_KEY"

curl https://api.axforge.ai/v1/chat/completions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen3.8-27b-nvfp4","messages":[{"role":"user","content":"Summarize DORA in one paragraph."}]}'
Chat, streaming, tools and vision: the full guide
# pip install openai · the key is read from AXFORGE_API_KEY
import os
from openai import OpenAI

client = OpenAI(base_url="https://api.axforge.ai/v1", api_key=os.environ["AXFORGE_API_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)
Chat, streaming, tools and vision: the full guide

Specifications

What is served

ModelQwen3.8 27B, dense 27B, latest Qwen generation
API model nameqwen3.8-27b-nvfp4
Context window262,144 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
RegionStockholm, Sweden (eu-se-1), and inference stays in-region
Input price€0.32 / 1M tokens
Output price€2.00 / 1M tokens

Performance

Community benchmark: labelled, not ours

MetricValueCondition
Decode speed (community)25.1 tokens/sSparkBench PBM @ 4k context, single GB10, NVFP4 + MTP
Concurrency6 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 262,144 tokens for document analysis, synthesis and multi-step tasks.
Streaming applicationsTokens stream as they are generated, for 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 from €0.85/hour by the hour, week, month or year: the same hardware class the API runs on, single-tenant, with full SSH access. 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. Dedicated GPU rentals run from Málaga, Spain (eu-es-1).

What does the Qwen3.8 27B API cost?

Launch pricing is €0.32 per million input tokens and €2.00 per million output tokens. No subscription, no minimum.

What is the context window?

262,144 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, from €0.85/hour by the hour, week, month or year. Check availability in the console, or Request deployment for a system AxForge operates for you.

Ready to build on EU inference?

Get API access Talk to an engineer

Explore

All models

Discuss

Comments

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