OpenAI-compatible
Same request and response shapes as /v1/chat/completions. Existing SDKs and tools work unchanged.
Every model, for free.
Inferlane is an OpenAI-compatible inference API. There is no price list, no credits and no card. The only cost is simple: the data you send is used for AI training.
The deal
Free models. Your data trains the next ones.
Instead of charging per token, Inferlane keeps every model free for everyone. In exchange, the prompts and completions you send through the API are used as training data for AI models. That's the whole arrangement — no hidden tiers, no upsells.
$0/ token, forever
Every model is free. The only cost being: the data you send will be used for AI training. Don't send anything you wouldn't want a model to learn from.
Why Inferlane
An inference API without the invoice
Point your existing OpenAI client at a new base URL, paste in your key, and keep shipping.
Every model, free
No per-model pricing, no premium tier. Anything listed in /v1/models is available to every account.
Streaming built in
Set stream: true and receive server-sent events token by token, exactly like upstream.
One key, no stats
Your dashboard holds exactly one thing: your API key. Rotate it any time. No usage graphs, no quotas to watch.
Quickstart
Two lines to switch
Change the base_url and the key. Everything else in your code stays where it is.
Grab your key from the dashboard after signing up.
from openai import OpenAI
client = OpenAI(
base_url="https://inferlane/v1",
api_key="YOUR_API_KEY",
)
response = client.chat.completions.create(
model="openai/gpt-oss-120b",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://inferlane/v1",
apiKey: "YOUR_API_KEY",
});
const response = await client.chat.completions.create({
model: "openai/gpt-oss-120b",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);curl https://inferlane/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-oss-120b",
"messages": [{"role": "user", "content": "Hello!"}]
}'
Catalogue
Available models
Live from /v1/models. Click any model to copy its ID.
FAQ
Questions, answered plainly
Is it really free? What's the catch?
Yes, every model is free. The catch is stated up front: the data you send — prompts and generated completions — is used as training data for AI models. If that's not acceptable for a given workload, don't send it here.
What should I not send?
Anything confidential, personal or regulated. Treat every request as if it will end up in a training set, because it will.
Do I need a credit card?
No. There is no billing system at all. Create an account with a username and password and your API key is ready.
Which SDKs work?
Anything that speaks the OpenAI chat completions API: the official Python and Node SDKs, LangChain, LiteLLM, SillyTavern, Open WebUI, coding agents, and plain HTTP.
Are there rate limits or quotas?
There are no quotas to manage and no usage statistics to watch. Requests are served on a best-effort basis; if a provider is temporarily down the API retries other providers for you.
Get your key in under a minute
Username, password, done. Every model unlocked.
Create a free account