OpenAI API

FUNCD provides OpenAI-compatible Chat Completions and Responses APIs at:

https://api.funcd.org/v1

Chat Completions

curl 'https://api.funcd.org/v1/chat/completions' \
  -H "Authorization: Bearer $FUNCD_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "tokener-gpt-5-6-luna",
    "messages": [{"role": "user", "content": "Hello"}],
    "max_tokens": 128
  }'

Python SDK

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["FUNCD_API_KEY"],
    base_url="https://api.funcd.org/v1",
)

response = client.chat.completions.create(
    model="tokener-gpt-5-6-luna",
    messages=[{"role": "user", "content": "Hello"}],
    max_tokens=128,
)
print(response.choices[0].message.content)

JavaScript SDK

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.FUNCD_API_KEY,
  baseURL: "https://api.funcd.org/v1",
});

const response = await client.chat.completions.create({
  model: "tokener-gpt-5-6-luna",
  messages: [{ role: "user", content: "Hello" }],
  max_tokens: 128,
});

console.log(response.choices[0].message.content);

Responses API

Use Responses for Codex CLI, function tools, and native streaming events.

response = client.responses.create(
    model="tokener-gpt-5-6-luna",
    input="Reply only with OK",
    store=False,
)
print(response.output_text)

Current scope

Standard responses, streaming, and local function tools are supported. Upstream session storage, previous_response_id, background tasks, and hosted web search are not currently exposed.

Streaming

Add the following field to the request:

{ "stream": true }

Read the stream through its final event. Missing or inconsistent usage is moved to billing review and is not treated as free usage.