Anthropic's fastest, cheapest model — near-instant replies.
No signup required — try it as a guest. 30,000 free tokens every day once you sign up.
Claude 3 Haiku is Anthropic's smallest, fastest model — small enough to be basically free per message on Faceb.ai's token economy, but still sharp for day-to-day tasks. Our cheapest Anthropic option.
Sub-second first-token latency
Cheap enough to run over large documents
200k context
Same careful tone as its bigger siblings
A few hundred tokens per message. Ideal for "cheap mass" work like summarising a bunch of docs.
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-haiku",
"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-haiku",
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-haiku",
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 Haiku is Anthropic's smallest and fastest model — released March 2024. Designed for high-volume, low-latency use cases.
Haiku for high-volume, short-turnaround tasks (summaries, classifications, tagging). Sonnet for anything that needs real reasoning.
You get 30k tokens free every day — a Haiku message costs a few hundred, so that's 70+ free messages a day, every day.
200,000 tokens — same as full Sonnet. Large input with cheap processing.
Yes — it accepts image input, just like the rest of the Claude 3 family.
Both are small-and-fast. Haiku has a larger context window (200k vs 128k); GPT-4o mini tends to score slightly higher on reasoning benchmarks. Pennies either way.
Yes — Anthropic designed it specifically for production chat and classification workloads. Many call-centre and moderation systems run on Haiku.
Yes — same tool-use API as Sonnet and Opus.
Yes. Model slug: anthropic/claude-3-haiku. API base: https://api.faceb.ai/v1.
Yes — Anthropic released Claude 3.5 Haiku in late 2024, and our picker has it too. Slight quality upgrade over 3 Haiku at similar cost.
On narrow tasks yes; on open-ended reasoning, probably not without a big new generation. Pick the right model per task — that's why we built the per-message switcher.
Same as the rest of Anthropic's API — traffic is not used for training, we don't store beyond your chat history, and the Privacy Policy spells out retention periods.
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 →OpenAI's fastest, cheapest frontier model — great default.
Chat with GPT-4o mini →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.