@munitoai/pi-provider0.1.0
Munito AI in pi: open models for Europe, private by default
Untested on omp
This is a pi package. No one has reported whether it works on omp yet. If you try it, add your result below.
Reports 0
No reports yet.
Readme
Munito AI for pi
This pi package makes Munito AI a model provider of pi. Munito AI serves open models for Europe, private by default, on an OpenAI-compatible API.
Install
pi install git:github.com/munitoai/pi-provider
Create an API key at console.munito.ai/keys.
In pi, run /login, pick Munito AI, and paste the key. Or set MUNITO_API_KEY in your environment.
Then run /model and pick a Munito AI model.
Providers
| Provider | Host | Use it when |
|---|---|---|
munito (Munito AI) |
https://api.munito.ai/inference/v1 |
Any region can process the request. |
munito-eu (Munito AI (EU)) |
https://api.eu.munito.ai/inference/v1 |
Each request must stay in the EU. |
Both use the same key.
Models
| Model | Context | Input |
|---|---|---|
zai-org/glm-5.3-flash |
1,048,576 | Text, images |
deepseek-ai/deepseek-v4-flash |
1,048,576 | Text |
deepseek-ai/deepseek-v4.1-flash-1017 (preview, munito only) |
1,048,576 | Text, images |
qwen/qwen3.8-27b |
262,144 | Text, images |
aleph-alpha/kolibri-1 |
1,048,576 | Text |
The prices are at docs.munito.ai/models. pi shows the cost of each session from them.
Reasoning
pi sends its thinking level as reasoning_effort, and Munito AI moves each level to the nearest level that the model has.
off sends none: the model stops its reasoning, and a model that always reasons, such as GLM-5.3-Flash, runs its lowest level.
See Reasoning models.
Prompt cache
pi sends the session ID in the header x-session-affinity, and Munito AI keeps the conversation on its prompt cache.
License
MIT