✨ One subscription. Every model.

Every AI in one chat.
Pay one bill, not ten.

Q: Do you have a developer API?

Yes. The /api/ page documents it. It's OpenAI-compatible (POST /v1/chat/completions) and uses the same credit balance as your chat account, so one wallet covers both.

Chat with GPT-4o, Claude 3.5 Sonnet, Gemini 2.0, Llama 3.3, DeepSeek, Grok, and 100+ more — without juggling subscriptions, tabs, or API keys.

Start chatting — no signup → See pricing

Faceb.ai

+ New chat

RECENT

Refactor my Django view

Trip plan: Lisbon, 7 days

Explain RAG in plain English

Cold-email subject lines

SQL: top customers by ARR

Logo concepts for a SaaS

Edit my About page copy

You

Refactor this Django view so the slow query is cached and the response stays under 200ms.

Assistant openai/gpt-4o

The bottleneck is the un-indexed .filter(user__email=…) hitting on every request. Wrap the query in cache.get_or_set with a 5-minute TTL and add a partial index:

pythonCopy

from django.core.cache import cache

def dashboard(request):
    key = f"dash:{request.user.id}"
    data = cache.get_or_set(
        key, lambda: heavy_query(request.user), 300
    )
    return JsonResponse(data)

That alone usually drops p95 from ~900ms to under 60ms once the cache is warm.

Try a different approach…

↑

The whole frontier in one box

No more \

OpenAI

GPT-4o

128k ctx · vision

OpenAI

GPT-4o mini

128k · fast & cheap

Anthropic

Claude 3.5 Sonnet

200k · top reasoning

Anthropic

Claude 3 Haiku

200k · low latency

Google

Gemini 2.0 Flash

fast · vision

Built for power users

Everything you'd expect from a serious AI workspace, with none of the lock-in.

⚡

Real streaming

Tokens flow in as they're generated, with markdown, code highlighting, and a stop button — not a \

🤖

12+ ready-made bots

Writing coach, code mentor, SQL whisperer, growth marketer, dungeon master… each tuned with the right system prompt and model.

🖼️

Image understanding

Drag in a screenshot, photo, or whiteboard — vision-capable models read it, transcribe it, and answer questions about it.

⚙️

Developer API

OpenAI-compatible POST /v1/chat/completions. Same credit balance as your chat. See the docs →

🔁

Edit, regenerate, branch

Bad answer? Regenerate. Bad question? Edit it and resubmit — the chat rewinds. Switch models mid-conversation.

🌓

Dark mode that doesn't suck

Inter font, generous whitespace, real syntax highlighting. Looks just as good at 11pm.

⚙️ Developer API

One key. Every model.

Drop-in OpenAI-compatible. Same credit balance as your chat — no separate plan, no separate billing. Switch from openai/gpt-4o to anthropic/claude-3.5-sonnet by changing one string.

One sk-faceb-… key for 100+ models
Streaming + non-streaming, OpenAI response shape
Credits charged shown on every response — no surprise invoices
No retention. We don't log prompts or responses.

Read the docs → All examples

curl https://api.faceb.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-faceb-YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-3.5-sonnet",
    "messages": [{"role":"user","content":"Hello!"}],
    "stream": true
  }'

from openai import OpenAI

client = OpenAI(
    base_url="https://api.faceb.ai/v1",
    api_key="sk-faceb-YOUR_KEY",
)

stream = client.chat.completions.create(
    model="openai/gpt-4o",
    messages=[{"role": "user", "content": "Write a haiku."}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="", flush=True)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.faceb.ai/v1",
  apiKey: "sk-faceb-YOUR_KEY",
});

const stream = await client.chat.completions.create({
  model: "google/gemini-2.0-flash-exp:free",
  messages: [{ role: "user", content: "Suggest a startup name." }],
  stream: true,
});
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || "");
}

Simple pricing

50k credits on signup. Upgrade when you need more.

Free

$0signup bonus

Kick the tires.

50,000 credits on signup (one-time)
Every model, no lock-out
All 12+ bots, image uploads

Start free Pro

$9.99/ mo billed yearly

$14.99 monthly · cancel anytime.

15,000,000 credits / month
≈ 3,900 GPT-4o or 39k GPT-4o-mini messages
Top-up packs from $5 / 1M credits
7-day money-back guarantee

Go Pro → Lifetime

$499one-time

Pay once. 15M credits / month forever.

Everything in Pro
No subscription — pay once, done
Pays for itself in ~3.5 years vs Pro
Priority support · all future models

Buy Lifetime

Frequently asked

How is this different from ChatGPT or Claude.ai?

ChatGPT only gives you OpenAI models. Claude.ai only gives you Anthropic. Faceb.ai gives you both, plus Gemini, Llama, DeepSeek, Grok, Mistral, Qwen and 100+ more — all from a single subscription, with one consistent UI, history, and bot library.

Where does the AI actually run?

Faceb.ai talks to each provider's official API on your behalf. Your messages aren't used to train any model and we never see them in plaintext beyond what's needed to route the request.

Do I keep my conversations if I cancel?

Yes. Your account, chat history, and saved bots stick around. To keep chatting after your Pro credits run out, top up a credit pack or re-subscribe.

Can I share a chat publicly?

Click the share icon in any chat and you get a clean read-only link you can hand to anyone — they don't need an account.

Are the cheap models any good?

Absolutely. Llama 3.3 70B, Mistral Small 3.1, Gemini 2.0 Flash and DeepSeek V3 are a fraction of the cost of GPT-4o and Claude Opus but get most day-to-day jobs done. Save the heavy models for when you actually need them and your credit pool lasts much longer.

Do you have a developer API?

Yes — it's OpenAI-compatible (POST /v1/chat/completions) and uses the same credit balance as your chat account, so one wallet covers both. See the docs →

Every AI in one chat.Pay one bill, not ten.