Model
Pixtral 12B (vision)
EU sovereignEU Sovereign · 90/100Call Pixtral 12B (vision) through an OpenAI-compatible API hosted in Europe: licence, real per-token price, hosting jurisdiction.
About this model
Pixtral-12B-2409 is a multimodal model from Mistral AI, released in September 2024 under the Apache 2.0 licence. According to its model card, it pairs a 12-billion-parameter multimodal decoder with a 400-million-parameter vision encoder, was trained natively on interleaved image and text data, and accepts images of variable sizes, several per message. Its sequence length is 128k tokens. The card reports 52.5 on MMMU, 81.8 on ChartQA and 90.7 on DocVQA, and says it keeps strong text-only results (69.2 on MMLU). It fits reading charts, documents and screenshots at a low price per token. Qwen3.6 35B is a newer, larger multimodal model in this catalogue.
Sources, checked on 20 October 2026: huggingface.co/mistralai/Pixtral-12B-2409 ↗
Specifications
- API model id
- pixtral-12b
- Availability
- Live
- Hosting jurisdiction
- EU sovereign
- Served via
- Scaleway
- Publisher
- Mistral AI (France)
- Parameters
- 12B
- Licence
- Apache-2.0
- Context window
- 128k
- Modality
- Vision-language
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
- Not assessed by us — training compute not published, or too close to the 10²⁵ FLOP threshold to call
- Data retention
- None at Frontière AI; Scaleway states prompts are not stored, except requests causing errors or abuse (kept up to 2 weeks)
Frontière Verified
Our 6-criteria checklist for this model. Each criterion is assessed independently — a checkmark means we ran, recorded and passed the check; an empty circle means not confirmed yet.
Compliance evidence
Provider facts for this model's serving path, as documented by Frontière AI; the retention row quotes each provider's own documentation where it exists. Dates reflect the most recent documented audit of each fact.
Last verified: 2026-08-13
- Provider / operator
- Scaleway Generative APIs
- Country
- France
- Ownership / control
- EU-controlled — no non-EU capital control
- Jurisdiction
- EU (observed serving region)
- Deployment
- Managed cloud inference
- Data retention
- None at Frontière AI; Scaleway states prompts are not stored, except requests causing errors or abuse (kept up to 2 weeks)
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 is run by a French provider (OVHcloud or Scaleway), in data centres in France. It is not a US company, so the CLOUD Act does not reach it the way it reaches a US provider, and under GDPR a foreign court order is only enforceable in the EU through an international agreement (Article 48). That is the SecNumCloud principle — who controls the operator matters more than where the servers sit — applied as a label, not a qualification: this service is not SecNumCloud-qualified. Our gateway runs in Vercel's Paris region (a US company): your prompts pass through it without being stored.
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: scaleway.
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="pixtral-12b",
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 and VAT included — not an infrastructure cost. No subscription: top up from €10; calls are refused once the balance reaches zero, and a call already running can take it slightly below — deducted from your next top-up.
What will it cost you?
Pick a workload or type your own token counts: the estimate uses the prices above, margin and VAT included.
Example workload
Roughly 1,000 tokens ≈ 750 English words.
No discounted cache rate on this model: every input token is billed at the input rate.
Per request
€0.00062
Per day
€0.6216
Per month
€18.65
30 days
A €10 top-up covers about 16,087 requests · Pixtral 12B
Where the money goes
- Input€15.12 · 81%
- Output€3.53 · 19%
Estimate, margin and VAT included, from the prices on this page. You are billed on the tokens the provider reports for each call, debited from a prepaid balance — no subscription.
FAQ
Is Pixtral 12B (vision) GDPR-compliant on Frontière AI?
It is the setup a GDPR assessment looks for: Pixtral 12B (vision) is served by Scaleway, a French company, in data centres in France — not a US provider, so outside the CLOUD Act's direct reach. Your prompts transit through our gateway, hosted by Vercel in Paris (a US company), without being stored: Frontière AI keeps only the token counts billing requires. Compliance also depends on your use and your data processing agreement.
How much does Pixtral 12B (vision) cost?
€0.0336 per 100,000 input tokens and €0.0336 per 100,000 output tokens — margin and VAT included, that is the amount debited from your prepaid balance. No subscription: you top up from €10; calls are refused once the balance reaches zero, and a call already running can take it slightly below — deducted from your next top-up.
How do I call Pixtral 12B (vision) from my code?
The API is OpenAI-compatible: point base_url at https://getfrontiereai.eu/api/v1, swap the key, and pass “pixtral-12b” as the model field. Your SDK, scripts and tools keep working, streaming included.
Under which licence is Pixtral 12B (vision) released?
Apache-2.0, a permissive licence. It covers the model weights published by Mistral AI (France); your use through Frontière AI's API is separately governed by our own terms.
Articles about this model
Other models in the catalog
Call it in minutes
Create an account, top up €10, change two lines.