Anthropic's best balance of quality and cost — a coder favourite.
No signup required — try it as a guest. 30,000 free tokens every day once you sign up.
Claude 3.5 Sonnet is Anthropic's best everyday model — consistently ranked top-tier for code, reasoning, and long-form writing. 200k context (paste entire codebases), careful tone, and refreshingly honest uncertainty.
State-of-the-art code generation — especially refactoring
200k context (largest of the frontier models)
Careful, calibrated tone — less over-confident than GPT-4o
Excellent at following detailed system prompts
Around 3,750–7,500 tokens per typical message. 15M Pro tokens buy ~2,000–4,000 Sonnet 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": "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="anthropic/claude-3.5-sonnet",
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: "anthropic/claude-3.5-sonnet",
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.
Claude 3.5 Sonnet is Anthropic's mid-size flagship — released June 2024. It replaced Claude 3 Opus as their best everyday model and powers most of the coding-tooling market (Cursor, Windsurf, many agents).
Most developers think so — Sonnet has been the default coding model on Cursor and Windsurf for months. It's especially strong on refactors and understanding existing codebases.
Yes. Faceb.ai gives you Sonnet alongside GPT-4o, Gemini and 100+ more on one $14.99/month plan — no Anthropic sub required.
Yes, natively. Drop a screenshot and it reads it.
200,000 tokens — larger than GPT-4o's 128k. Enough to paste entire medium-size codebases.
Around 3,750–7,500 tokens for a typical exchange. 15M Pro tokens buy roughly 2,000–4,000 Sonnet messages.
Anecdotally yes — Anthropic's training emphasises calibrated uncertainty. It's more willing to say "I don't know" or flag a guess.
Yes — the picker has Claude 3 Haiku (fastest/cheapest Anthropic) and Claude 3 Opus (larger, pricier). Switch per message.
Yes. Your API keys work with any model slug — use anthropic/claude-3.5-sonnet with the OpenAI SDK pointed at https://api.faceb.ai/v1.
Roughly April 2024 for the current version — it gets refreshed occasionally.
Yes — Anthropic's tool-use API is supported. Your client library just needs to pass the tools list in the request.
We don't store prompts beyond your chat history, and we don't train on them. Anthropic's policy prohibits training on API traffic.
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 →Google's fast multimodal model with a 1M-token context window.
Chat with Gemini 2.0 Flash →Anthropic's fastest, cheapest model — near-instant replies.
Chat with Claude 3 Haiku →One subscription covers every frontier model — switch between them per message. No extra API keys, no extra bills.