Call open models through an OpenAI- and Anthropic-compatible API, hosted in Europe.
Open models
for Europe.
Fast and reliable API, compatible with major SDKs and agents.
Private by default, zero data retention.
Munito AI serves open models through an OpenAI- and Anthropic-compatible API. Your requests run in the EU or the US, and you pay for each token or each page.
curl https://api.munito.ai/inference/v1/chat/completions \
-H "Authorization: Bearer $MUNITO_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "qwen/qwen3.8-27b", "messages": [{"role": "user", "content": "Hello"}]}'Quickstart
Create a key and send your first request.
Models
The open models, their context and their regions.
Pricing
The price of each model, for each region and tier.
Compatibility
Use your OpenAI or Anthropic SDK. Change the base URL.
Document AI
Read PDFs and images into Markdown.
Sandboxes
A Linux microVM for your agents and your code.
Recipes
Build search, extraction, support, and transcript summaries.
Base URLs
| Host | Base URL |
|---|---|
| Global | https://api.munito.ai/inference/v1 |
| EU | https://api.eu.munito.ai/inference/v1 |
| US | https://api.us.munito.ai/inference/v1 |
The EU and US hosts keep processing in their region. See Regions.
Docs for agents
llms.txt lists the pages, and llms-full.txt holds the full docs as Markdown.