Build against one free API.

Get a key

Join Discord and run /signup. Send the key as a bearer token. If you lose it, run /resetkey.

Base URL: https://api.freetheai.xyz/v1
Auth:     Authorization: Bearer YOUR_API_KEY

Supported routes

OpenAI-compatible chat

Point OpenAI-compatible clients at https://api.freetheai.xyz/v1. Use exact model aliases from /models.

curl https://api.freetheai.xyz/v1/chat/completions \
  -H "Authorization: Bearer $FREETHEAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm/glm-5.1",
    "messages": [
      { "role": "user", "content": "Write a tiny Flask route." }
    ],
    "stream": true
  }'

import OpenAI from "openai";

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

const res = await client.chat.completions.create({
  model: "glm/glm-5.1",
  messages: [{ role: "user", content: "Reply with OK." }]
});

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

Anthropic-style clients

Use /v1/messages for clients that expect Anthropic-style request bodies.

curl https://api.freetheai.xyz/v1/messages \
  -H "Authorization: Bearer $FREETHEAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "rev/claude-sonnet-4.5",
    "max_tokens": 256,
    "messages": [
      { "role": "user", "content": "Give me a short implementation plan." }
    ]
  }'

List models

Use /v1/models for normal clients. Use /v1/models/full when you need tier and catalog metadata for a UI.

curl https://api.freetheai.xyz/v1/models \
  -H "Authorization: Bearer $FREETHEAI_API_KEY"

curl "https://api.freetheai.xyz/v1/models/full" \
  -H "Authorization: Bearer $FREETHEAI_API_KEY"

Generate and edit images

Use /v1/images/generations for text-to-image. Use /v1/images/edits only with img/gpt-image-2. Generation responses may contain either b64_json or url, so robust clients should support both.

curl https://api.freetheai.xyz/v1/images/generations \
  -H "Authorization: Bearer $FREETHEAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "vhr/gpt_image_2",
    "prompt": "A cinematic neon sports car parked under rainy city lights"
  }'

curl https://api.freetheai.xyz/v1/images/edits \
  -H "Authorization: Bearer $FREETHEAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "img/gpt-image-2",
    "prompt": "Improve this logo and make it cleaner",
    "image": "data:image/png;base64,BASE64_IMAGE_HERE"
  }'

Python save helper

import base64
import os
from pathlib import Path

import requests

API_KEY = os.environ["FREETHEAI_API_KEY"]
API_BASE = "https://api.freetheai.xyz/v1"


def save_image_result(result, output_path):
    item = (result.get("data") or [{}])[0]
    if item.get("b64_json"):
        Path(output_path).write_bytes(base64.b64decode(item["b64_json"]))
        return
    if item.get("url"):
        image = requests.get(item["url"], timeout=120)
        image.raise_for_status()
        Path(output_path).write_bytes(image.content)
        return
    raise RuntimeError(f"No image found in response: {result}")


res = requests.post(
    f"{API_BASE}/images/generations",
    headers={
        "Authorization": f"Bearer {API_KEY}",
        "Content-Type": "application/json",
    },
    json={
        "model": "vhr/gpt_image_2",
        "prompt": "A clean product mockup on a dark desk",
    },
    timeout=180,
)
res.raise_for_status()
save_image_result(res.json(), "generated.png")

Common responses