onomeoonomeoBeta
Feedback
All tools

Use onomeo in AnythingLLM

AnythingLLM is a desktop app for chatting with your documents. Follow the four steps below to set onomeo as its model service and chat with this site's models.

A desktop app for chatting with your documents.

What to fill in

OpenAI-compatible

Use these details in any OpenAI-compatible tool.

Base URL
https://onomeo.com/v1
API key
Model

No key yet? Create one on the My account page, then come back — the fields below fill in by themselves. Go to My account

Step by step

  1. Choose Manual set up

    Download AnythingLLM from anythingllm.com, open it and press Get Started. On the Set Up options screen, press Manual set up below. Do not press the arrow on the right: that downloads a local model of about 3 GB.

    AnythingLLM's Set Up options screen: Manual set up below the suggested local model
    Press Manual set up.

  2. Choose Generic OpenAI

    On the LLM Preference screen, type generic in the search box and press Generic OpenAI.

    AnythingLLM's provider search: with generic typed, Generic OpenAI appears
    With generic typed, press Generic OpenAI.

  3. Fill the address, key and model

    Base URL: the address below. API Key: your key (copy it from "What to fill in" above). Once both are in, Selected Model turns into a list: choose auto. Model context window: type 128000; leave Max Tokens as it is. Then press the arrow on the right.

    https://onomeo.com/v1
    AnythingLLM's Generic OpenAI form: the address https://onomeo.com/v1, the key, the model auto and a context window of 128000
    Fill the four places marked, then press the arrow on the right.

    If Selected Model does not turn into a list, the address or the key is wrong; check them again.

  4. Start chatting

    The survey that follows is optional: press the arrow on the right. Press the arrow again on Data Handling & Privacy, and close the feature tour that pops up. Type a message in the input box and press Enter.

    An AnythingLLM chat: the model at the top left is auto, and the assistant has answered a message
    A reply means the connection works. auto at the top left is this site's model.

    Each message counts as 1 call. Measured on 9 October 2026 with AnythingLLM 1.17.0: the message above took 1 call on auto and was not charged.

If it will not connect

  • Keep /v1 at the end of the Base URL and add nothing after it.
  • To change the model later, press the wrench icon at the bottom left to open the settings, and change Selected Model under AI Providers, LLM.
  • 401: the key is wrong; correct API Key in the same place. 402: insufficient balance. Claude, GPT and other big models are charged by usage; top up on the Pricing page or switch to a free model.
  • Once your own provider keys are connected on the My providers page, their models also appear in the Selected Model list, with names starting my/. This site does not charge for those calls.
AnythingLLM's own documentation