OpenAI's flagship multimodal model — text, vision, and code.
No signup required — try it as a guest. 30,000 free tokens every day once you sign up.
GPT-4o is OpenAI's flagship omni model — the same brain powering ChatGPT Plus, but accessed per-message through Faceb.ai instead of a flat monthly fee. It handles text, images, and code equally well, with 128k context and low-latency streaming.
General-purpose reasoning that matches or beats GPT-4 Turbo
Native vision — paste screenshots, diagrams, photos
Fast code generation with solid context tracking
Low-latency streaming feels conversational
Around 3,750–9,200 tokens per typical message. 15M Pro tokens buy roughly 1,600–4,000 GPT-4o messages.
OpenAI-compatible. Same Faceb.ai tokens cover chat and API. Drop-in replacement for the OpenAI SDK.
curl https://api.faceb.ai/v1/chat/completions \
-H "Authorization: Bearer sk-faceb-YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-4o",
"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": "Hello!"}],
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: "openai/gpt-4o",
messages: [{ role: "user", content: "Hello!" }],
stream: true,
});
for await (const chunk of stream) {
process.stdout.write(chunk.choices[0]?.delta?.content || "");
}
Also works for image generation (image-output model slugs return image_url content parts) and web search (add "web_search": true to the payload). Same endpoint, same wallet.
GPT-4o ('o' for omni) is OpenAI's flagship multimodal model — text, vision, and speech in a single network. Released May 2024 and still the default for ChatGPT Plus subscribers.
You get 30,000 tokens every day on the free plan — enough for around 6–8 GPT-4o messages a day. Need more? Pro is $14.99/month for 15M tokens (hundreds of GPT-4o messages) or pay-as-you-go top-ups from $5.
Faceb.ai doesn't lock you to OpenAI. The same $14.99/month lets you switch to Claude 3.5 Sonnet, Gemini 2.0 Flash, Llama 3.3, DeepSeek V3, Grok 2 or 100+ other models per message. No extra subscriptions needed.
Yes — drop any image in the chat and GPT-4o reads it natively. It handles screenshots, diagrams, handwriting, photos.
128,000 tokens — about 300 pages of text. Enough to paste a whole chapter, a long PDF, or a small codebase.
It's very solid, but most developers prefer Claude 3.5 Sonnet for refactors and architecture work. For generating new code from a spec, GPT-4o holds its own.
Yes. Any API key you create at /account/api/ can call GPT-4o at api.faceb.ai/v1/chat/completions — the OpenAI SDK works out of the box. Point base_url at https://api.faceb.ai/v1.
Around 3,750–9,200 tokens for a typical exchange (200-token prompt + 400-token reply). Short questions are cheaper; long essay generation is pricier.
No. We contractually request that upstream providers not train on content routed through us. See our Privacy Policy.
Yes — the model picker at the top of the chat lets you change per message. Previous context carries over.
GPT-4o mini is 20-30× cheaper per token but a weaker reasoner. Use mini for volume work; pick full GPT-4o when quality matters most.
Yes — our model catalog is fetched from the upstream aggregator, so new OpenAI releases appear in the picker as soon as they're generally available.
Your Faceb.ai tokens work for every model — switch per message, no extra subscriptions.
Anthropic's best balance of quality and cost — a coder favourite.
Chat with Claude 3.5 Sonnet →Google's fast multimodal model with a 1M-token context window.
Chat with Gemini 2.0 Flash →OpenAI's fastest, cheapest frontier model — great default.
Chat with GPT-4o mini →One subscription covers every frontier model — switch between them per message. No extra API keys, no extra bills.