Model
Qwen3.8 27B (multimodal)
EU sovereignEU Sovereign · 90/100Call Qwen3.8 27B (multimodal) through an OpenAI-compatible API hosted in Europe: licence, real per-token price, hosting jurisdiction.
€0.056
Input — per 100k tokens
€0.378
Output — per 100k tokens
Specifications
- API model id
- qwen3.8-27b
- Availability
- Live
- Hosting jurisdiction
- EU sovereign
- Served via
- ovhcloud
- Publisher
- Qwen
- Parameters
- 27.8B
- Licence
- Apache-2.0
- Context window
- 256k
- Modality
- Multimodal (text + image)
Reasoning model — thinks before answering. Omit max_tokens or allow at least ~1,000.
Open weights & AI Act facts
Factual characteristics of this model's weights — stated, not certified. Under the EU AI Act, whether a deployment is compliant depends on the model, your role and your use case.
- Open weights
- Weights public and freely executable
- AI Act class
- GPAI — general-purpose AI
- Systemic risk
- Below the systemic-risk threshold
- Data retention
- Zero prompt / completion retention
Frontière Verified
This model has been verified against our 6-criteria checklist before going live. Each criterion is assessed independently — a checkmark means we confirmed it.
Compliance evidence
Provider facts for this model's serving path, as verified and documented by Frontière AI. Dates reflect the most recent documented audit of each fact.
Last verified: 2026-07-31
- Provider / operator
- OVHcloud AI Endpoints
- Country
- France
- Ownership / control
- EU-controlled — no non-EU capital control
- Jurisdiction
- EU (observed serving region)
- Deployment
- Managed cloud inference
- Data retention
- Zero prompt / completion retention
Frontière AI retains neither prompts nor completions from API calls; processing is structured to fit a short DPA (Art. 28 GDPR). DPA and subprocessor documentation available on request.
What its label means
This model runs on a provider with no non-EU capital or jurisdictional control, so a US court order cannot compel access to what it processes for you. That is the SecNumCloud principle: what decides exposure is who controls the operating company, not where the servers sit.
How we draw the line: GDPR vs. the CLOUD Act →Sovereignty Score — 90/100
Deterministic 0–100 score computed from the five factors below — ownership, hosting jurisdiction, cloud-provider control, data retention, deployment control. Full methodology: How Frontière AI determines sovereignty →
- Operating-company ownership
- 40/40
- Hosting jurisdiction (observed)
- 30/30
- Cloud-provider control
- 10/15
- Data retention
- 10/10
- Deployment control
- 0/5
Effective provider assessed: ovhcloud.
Calling it
The API is OpenAI-compatible. Change base_url and the key, then use this model id:
client = OpenAI(
base_url="https://getfrontiereai.eu/api/v1",
api_key=os.environ["FRONTIERE_KEY"],
)
reply = client.chat.completions.create(
model="qwen3.8-27b",
messages=[{"role": "user", "content": "Bonjour"}],
)One key covers the whole catalog — you switch models by changing a single string.
API reference →Pricing
The price you see is the price debited from your prepaid balance, margin included — not an infrastructure cost. No subscription: top up from €10, calls stop at zero.
FAQ
Is Qwen3.8 27B (multimodal) GDPR-compliant on Frontière AI?
Yes. Qwen3.8 27B (multimodal) is served through ovhcloud, a provider with no non-EU capital control, so your prompts stay beyond the reach of a US court order. Frontière AI additionally stores neither prompts nor completions from API calls — only the token counts billing requires.
How much does Qwen3.8 27B (multimodal) cost?
€0.056 per 100,000 input tokens and €0.378 per 100,000 output tokens — margin included, that is the amount debited from your prepaid balance. No subscription: you top up from €10 and calls stop when the balance reaches zero.
How do I call Qwen3.8 27B (multimodal) from my code?
The API is OpenAI-compatible: point base_url at https://getfrontiereai.eu/api/v1, swap the key, and pass “qwen3.8-27b” as the model field. Your SDK, scripts and tools keep working, streaming included.
Under which licence is Qwen3.8 27B (multimodal) released?
Apache-2.0, a permissive licence. It covers the model weights published by Qwen; your use through Frontière AI's API is separately governed by our own terms.
Is there any behaviour I should know about?
Reasoning model — thinks before answering. Omit max_tokens or allow at least ~1,000.
Other models in the catalog
Call it in minutes
Create an account, top up €10, change two lines.