Free & Open Inference

Free LLM Inference.
No Auth. No Limits.

OpenAI-compatible API you can start using right now. No accounts, no API keys, no rate limits. Just send a request.

Get Started Learn More
⚠️

Heads up: In exchange for free inference, we log every request — prompts, completions, metadata, everything. This data may be stored, distributed, or sold. Don't send anything you wouldn't want public. Read the Terms of Service and Privacy Policy.

How it works

Three steps. No signup.

1

Pick a model

Check /v1/models for the list of available models. We provide access to various open and commercial LLMs.

2

Send a request

Use the standard OpenAI chat completions format. Point any compatible library or tool at our endpoint. Streaming supported.

3

That's it

No API keys, no OAuth, no rate limits, no waiting lists. Just point your client at https://logfare.logorhythms.dev/v1 and go.

Quickstart

Copy, paste, run.

curl 
# Chat completion
curl https://logfare.logorhythms.dev/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
  "model": "your-model-id",
  "messages": [
    {"role": "user", "content": "Hello!"}
  ]
}'
Python (openai library) 
from openai import OpenAI

client = OpenAI(
    base_url="https://logfare.logorhythms.dev/v1",
    api_key="not-needed",  # anything works
)

response = client.chat.completions.create(
    model="your-model-id",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
POST /v1/chat/completions
GET /v1/models

About Logfare

A project by Logorhythms.

Logfare is operated by Logorhythms, an independent research and engineering group focused on AI infrastructure and open tooling.

We run this as a free, community resource. There are no uptime guarantees—this is provided as-is. In return for free access, all API traffic is logged for research and data purposes. If that's not for you, that's okay — but please read the Terms and Privacy Policy before using the service.

Visit logorhythms.dev →