xAI's conversational model — blunt, fast, current.
No signup required — try it as a guest. 30,000 free tokens every day once you sign up.
Grok 2 is xAI's conversational model — the one powering Grok on X. Blunter and more willing to take a stance than the big-lab models, with its own ingest of recent events. On Faceb.ai you get it without a Premium X subscription.
Less hedged, more opinionated tone
Current knowledge cutoff
131k context
Similar ballpark to GPT-4o per message.
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": "x-ai/grok-2-1212",
"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="x-ai/grok-2-1212",
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: "x-ai/grok-2-1212",
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.
Grok 2 is xAI's conversational model — the one powering the Grok assistant on X (formerly Twitter). Released in August 2024, positioned as less filtered and more willing to take a stance than the big-lab models.
No. Faceb.ai gives you Grok 2 on your regular plan — no X subscription required.
You get 30k tokens free every day. A Grok 2 message is in the GPT-4o cost ballpark, so the daily allowance covers a handful of messages every day.
Grok is tuned to be more opinionated and less hedged. Some prompts that GPT-4o refuses or waffles on, Grok will answer directly. Quality-wise it's in the frontier tier but slightly behind GPT-4o and Claude on benchmarks.
131,000 tokens — comparable to GPT-4o.
On Faceb.ai we use the standard Grok 2 API which has the model's training-time knowledge. The real-time X/Twitter integration is an X-product feature, not available through the API.
Decent but not a top pick — for code, Claude 3.5 Sonnet and DeepSeek V3 are stronger. Grok is better for general chat and opinion-heavy tasks.
Yes — model slug: x-ai/grok-2-1212. OpenAI-compatible at https://api.faceb.ai/v1.
Grok 2 Vision is a separate model; the picker has both the text-only and vision variants.
Roughly mid-2024, with periodic refreshes from xAI.
We route through the xAI API, not the X product. xAI's developer API terms don't include training on customer traffic.
As soon as xAI ships it publicly and our upstream aggregator lists it, yes.
Your Faceb.ai tokens work for every model — switch per message, no extra subscriptions.
OpenAI's flagship multimodal model — text, vision, and code.
Chat with GPT-4o →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 →One subscription covers every frontier model — switch between them per message. No extra API keys, no extra bills.