Sovereign inference.
Built for privacy.

Open-model APIs for text generation and document OCR. Keep customer data private, control where inference runs, and retain the freedom to switch.

Request early accessExplore models

Private beta Built in Europe

Input

Choose the next step for a support agent. Two settled €1,000 payments reference invoice 0417. Only one payment is due. Refunds need human approval.

Open model. Privacy by design.

Output

Next action: Request refund approval. Reason: Duplicate €1,000 payment. After approval: Refund and notify the customer.

Zero data retention by default

Familiar APIs. More freedom to choose.
  • OpenAI API format
  • Anthropic API format

From prompts to documents.

Use open models for text and document workloads through one platform.

Inference

Generate text, summarize content, and extract information from text.

Available in private beta

Qwen3.8

OpenAI and Anthropic API formats · Billed by the token

Language models and prices

Document AI

Turn PDFs, scans, and forms into text and Markdown for your application.

Available in private beta

LightOnOcr-2

Document OCR API · Billed by the page

Document AI models and prices

Built for developers.

Use familiar SDKs with your Munito API key. Choose a supported model and connect through OpenAI or Anthropic API formats.

Keep your integration portable.

Use standard API formats to reduce integration changes when you switch providers.

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.munito.ai/inference/v1",
    api_key=os.environ["MUNITO_API_KEY"],
)

response = client.chat.completions.create(
    model="qwen/qwen3.8-27b",
    messages=[{"role": "user", "content": "Hello, Munito."}],
)

print(response.choices[0].message.content)
# Example response: Hello! How can I help?
Copy code

Built for enterprise.

Clear controls for sensitive workloads. Visibility into how your data is processed.

Privacy

Keep customer data private.

Zero data retention by default. No training without your permission.

Privacy policy
Sovereignty

Control where inference runs.

Run inference in a region that meets your data residency requirements. EU processing is available today.

Available regions
Independence

Keep the freedom to switch.

Choose supported open models and connect through familiar API formats.

Explore open models

Choose where Munito runs.

Start with our serverless API. Future deployment options will bring Munito to infrastructure you control.

Private beta

Serverless

Access open models through Munito’s serverless API.

Planned

Bring Your Own Cluster

Deploy Munito into a Kubernetes cluster you control.

Planned

On-premises

Deploy Munito within your own infrastructure and facilities.

Need deployment on your infrastructure? Discuss your requirements

Coming next

  • Enterprise identity
  • Dedicated capacity
  • SLAs
  • ISO/IEC 27001Information security certification planned
  • SOC 2 Type IIAudit planned

Before you build.

Build with open models.
Keep control of your data.

Tell us what you want to build and where your data needs to be processed.

Request early access

Private beta