Getting started

Quickstart

Mint a key, change one URL, make a call.

Preview specification. The API opens at launch; this page describes the interface it will serve.

1. Get a key

Open the dashboard, connect a wallet on Robinhood Chain, pick a deposit and sign. The key is displayed once, so keep it somewhere safe. Working from a terminal instead? The prepaid keys page covers the scripted flow.

2. Chat completions

python

from openai import OpenAI

client = OpenAI(base_url="https://inferlane.xyz/v1", api_key="il_sk_...")

answer = client.chat.completions.create(
    model="meta-llama/llama-3.3-70b-instruct",
    messages=[{"role": "user", "content": "Name three uses for a router."}],
)
print(answer.choices[0].message.content)

typescript

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://inferlane.xyz/v1", apiKey: process.env.INFERLANE_KEY });

const answer = await client.chat.completions.create({
  model: "meta-llama/llama-3.3-70b-instruct",
  messages: [{ role: "user", content: "Name three uses for a router." }],
});

curl

curl https://inferlane.xyz/v1/chat/completions \
  -H "Authorization: Bearer $INFERLANE_KEY" \
  -H "content-type: application/json" \
  -d '{"model":"meta-llama/llama-3.3-70b-instruct","messages":[{"role":"user","content":"ping"}]}'

Streaming works as usual with stream: true. Add stream_options: {"include_usage": true} to receive token counts in the final chunk.

3. See what it cost

Every non-streaming response carries its exact charge in the headers:

response headers

X-Inferlane-Charge-USD: 0.000184
X-Inferlane-Cache: MISS
X-Inferlane-Route: meta-llama

Balance and recent calls appear on the dashboard and at GET /v1/keys/me.

NextModels →