API keys

Spend the compute pool from your own code. The endpoint is OpenAI shaped, so an existing client works by changing the base URL and the key. Any wallet that has launched a token can create one.

Pool available: $5.7K
Callable models: 12

Connect to manage keys

Use the wallet you launched with. Keys belong to that address.

Quickstart

Point any OpenAI client at the base URL and pass your key. The model is the OpenRouter id of a model a token backs.

Requestcurl

curl https://llmtokens.fun/api/v1/chat/completions   -H "Authorization: Bearer llm_sk_..."   -H "Content-Type: application/json"   -d '{    "model": "anthropic/claude-opus-5",    "messages": [{ "role": "user", "content": "Hello" }]  }'

Nodetypescript

import OpenAI from "openai"; const client = new OpenAI({  apiKey: process.env.LLMTOKENS_API_KEY,  baseURL: "https://llmtokens.fun/api/v1",}); const res = await client.chat.completions.create({  model: "anthropic/claude-opus-5",  messages: [{ role: "user", content: "Hello" }],});

Pythonpython

import osfrom openai import OpenAI client = OpenAI(    api_key=os.environ["LLMTOKENS_API_KEY"],    base_url="https://llmtokens.fun/api/v1",) res = client.chat.completions.create(    model="anthropic/claude-opus-5",    messages=[{"role": "user", "content": "Hello"}],)

Response headers

Every response reports what the call cost and what is left, so a client never needs a second request to find out.

x-compute-charged-micro-usdCost of this call, in millionths of a dollar.

x-compute-remaining-micro-usdPool balance after the call.