Choose your language
After signing in, we auto-mint a key tied to your account. Use it as the Bearer token for our OpenAI-compatible API at /api/chat.
Sign in to reveal your key
We sent a code to
90 text models across 10 providers, 26 image models, 25 video models — all with transparent pricing sourced directly from each provider's official API docs. The marquee animation you see here is rebuilt entirely in code: 4,440 measured halftone dots, motion-captured pixel sprites, zero image assets.
OpenAI's most powerful model family — three tiers for every task. Sol for maximum intelligence, Terra for balanced performance, Luna for speed.
Anthropic's most capable model — for ambitious, long-running, asynchronous work. Best for deep research, complex codebases, and large-context reasoning.
New dedicated generation tab with 26 image models and 25 video models. Canvas dot animation plays while generating, with smooth reveal transition. Download any result instantly.
https://unlimited-ai.pages.dev/api
Generate an API key in Settings. Include it via:
Authorization: Bearer YOUR_API_KEY
POST /api/chat
Content-Type: application/json
Authorization: Bearer YOUR_KEY
{
"model": "auto",
"messages": [{"role": "user", "content": "Hello"}],
"stream": true
}
POST Streams SSE responses. Compatible with OpenAI SDKs.
GET /api/health
Returns { ok: true, apiKeys, resend, abacus } status.
POST /api/auth/send-code
{"email": "user@example.com"}
POST /api/auth/verify-code
{"email": "user@example.com", "code": "123456"}
Returns { token, user }.
GET /api/models
POST /api/chat {"model": "claude-fable-5", ...}
Available models: auto (SMR), claude-fable-5, claude-opus-4.8, gpt-5.6-sol, gpt-5.5, gemini-3.1-pro, grok-4.5, deepseek-v4-pro, kimi-k2.7, glm-5.2, qwen-3.7-max, and 60+ more.
from openai import OpenAI
client = OpenAI(base_url="https://unlimited-ai.pages.dev/api", api_key="YOUR_KEY")
stream = client.chat.completions.create(model="auto", messages=[{"role":"user","content":"Hi"}], stream=True)
for chunk in stream: print(chunk.choices[0].delta.content or "", end="")
import OpenAI from 'openai';
const client = new OpenAI({ baseURL: 'https://unlimited-ai.pages.dev/api', apiKey: 'YOUR_KEY' });
import anthropic client = anthropic.Anthropic(base_url="https://unlimited-ai.pages.dev", api_key="YOUR_KEY")
Signed-in users get 50 credits/day (flat rate). Model costs vary from 0 (free) to 15 credits per message. Unused credits do not roll over. Rate limits are enforced per-account.
Publish your workspace app to a live URL. Choose a hosted domain or bring your own.