auto

Picked by onomeo for each request

Reads images: a question can carry pictures.

Model name for the APIauto

Uptime, last 3 days: 90%; 1,853 calls counted
Price per reply: Free; Limited by number of calls

Your chats and training

Not used for training.

The company that answers for this model states in its own terms that it does not use prompts or replies to train its models.

Which company answers for a model is not published here, so this says what the policy is, not whose it is. Checked against their terms on Sep 28, 2026.

Use in chat API docs

How auto picks a model

Each request goes to the model that has been answering best. A model that failed in the last 10 minutes waits its turn, and models under 80% uptime over the last 3 days go to the back.

If the model picked fails, the next one is tried, up to 3 models for one request. Only a reply you receive counts; a request no model could answer is neither counted as a call nor charged, except that a request the provider rejects as invalid (too long, for example) counts as one call.

Every reply names the model that wrote it.

Models it picks from, in the current order

Call it through the API

Any OpenAI-compatible client works: use the address in the sample and this model name.

import requests

response = requests.post(
    "https://onomeo.com/v1/chat/completions",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={"model": "auto", "messages": [
        {"role": "user", "content": "Hello!"}
    ]}
)
print(response.json())

Figures come from real calls made through this site. Models are served by third-party providers and may slow down or be withdrawn; this page follows those changes.