API reference

Inferlane exposes an OpenAI-compatible HTTP API. If your code already talks to OpenAI, switch the base URL and API key and it talks to Inferlane.

The deal: every model is free. The only cost is that the data you send — prompts and completions — is used for AI training. Do not send confidential or personal data.

Overview

Base URL: https://inferlane/v1
Authentication: bearer token (your API key) on /v1/chat/completions
Formats: JSON requests, JSON or text/event-stream responses
Compatible with the official OpenAI SDKs for Python and Node.js

Authentication

Create an account on the registration page; an API key is generated immediately and shown in your dashboard. Keys look like sk-qrd-… followed by 48 hex characters.

Send the key in the Authorization header:

HTTP header

Authorization: Bearer YOUR_API_KEY

You can rotate the key from the dashboard at any time; the previous key stops working instantly.

Base URL & SDK setup

from openai import OpenAI

client = OpenAI(
    base_url="https://inferlane/v1",
    api_key="YOUR_API_KEY",
)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://inferlane/v1",
  apiKey: "YOUR_API_KEY",
});

List models

GET /v1/models

Returns every model currently available. This endpoint does not require an API key, so you can open it directly: /v1/models.

Query parameters

Name	Type	Description
`type`	string	Only return models of this type, e.g. `chat`.
`provider`	string	Only return models served by the given upstream provider.

for model in client.models.list().data:
    print(model.id)

const models = await client.models.list();
for (const m of models.data) console.log(m.id);

curl https://inferlane/v1/models

Response

200 OK

{
  "object": "list",
  "data": [
    { "id": "openai/gpt-oss-120b", "object": "model", "type": "chat" }
  ]
}

Chat completions

POST /v1/chat/completions

Generates a model response for a conversation. Requires an API key. Any chat model ID from /v1/models is accepted.

Request body

Field	Type	Description
`model`	string, required	Model ID, e.g. `openai/gpt-oss-120b`.
`messages`	array, required	Conversation as `{ role, content }` objects. Roles: `system`, `user`, `assistant`, `tool`.
`stream`	boolean	When `true`, the response is streamed as server-sent events.
`n`	integer	Number of completions to generate. Defaults to 1.
`temperature`, `max_tokens`, `top_p`, `tools`, …	various	Standard OpenAI parameters are forwarded to the model where supported.
`provider`	string	Optional. Pin the request to a specific upstream provider listed for the model; otherwise one is chosen automatically.

response = client.chat.completions.create(
    model="openai/gpt-oss-120b",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello! How are you today?"},
    ],
)
print(response.choices[0].message.content)

const response = await client.chat.completions.create({
  model: "openai/gpt-oss-120b",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "Hello! How are you today?" },
  ],
});
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": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello! How are you today?"}
    ]
  }'

Response

200 OK

{
  "id": "chatcmpl-…",
  "object": "chat.completion",
  "created": 1710000000,
  "model": "openai/gpt-oss-120b",
  "choices": [
    {
      "index": 0,
      "message": { "role": "assistant", "content": "Hello! I'm doing well…" },
      "finish_reason": "stop"
    }
  ],
  "usage": { "prompt_tokens": 23, "completion_tokens": 12, "total_tokens": 35 }
}

Streaming

Set "stream": true to receive text/event-stream chunks in the OpenAI chat.completion.chunk format, terminated by data: [DONE].

stream = client.chat.completions.create(
    model="openai/gpt-oss-120b",
    messages=[{"role": "user", "content": "Write a haiku about lanes."}],
    stream=True,
)
for chunk in stream:
    delta = chunk.choices[0].delta.content
    if delta:
        print(delta, end="", flush=True)

const stream = await client.chat.completions.create({
  model: "openai/gpt-oss-120b",
  messages: [{ role: "user", content: "Write a haiku about lanes." }],
  stream: true,
});
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}

Errors

Errors follow the OpenAI envelope: { "error": { "message", "type", "code" } }.

Status	Code	Meaning
`400`	—	Missing `model`/`messages`, or the model is not a chat model.
`401`	`invalid_api_key`	No bearer token, or the key is malformed.
`403`	`invalid_api_key` / `expired_api_key`	The key is unknown (rotated or deleted) or expired. Get the current one from your dashboard.
`404`	—	Unknown model ID. Check `/v1/models`.
`500`	`internal_error`	Upstream failure after retries. Retry the request.

Data & training

Inferlane is free because the requests flowing through it are valuable as training data. Concretely: the prompts you send and the completions you receive through /v1/chat/completions are used for AI training.

Every model is free, for every account, with no tiers.
Assume anything you send may be learned by a future model.
Do not send secrets, personal data or anything under a confidentiality obligation.
Your account holds only a username, a salted password hash and your API key. There are no usage statistics.