Chat with Sonar

Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking t

No signup required — try it as a guest. 30,000 free tokens every day once you sign up.

Provider
Perplexity
Model slug
perplexity/sonar
Typical cost
Around 899–2,250 tokens per typical message. 15M Pro tokens buy roughly 6,666–16…
Availability
On Faceb.ai · chat + API

About Sonar

Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features...

What it's good at

1

127,072-token context window — enough for long documents.

2

Hosted by Perplexity — you can access it here alongside GPT-4o, Claude, Gemini and 100+ more on one plan.

3

Switch to any other model mid-conversation from the picker.

Pricing on Faceb.ai

Around 899–2,250 tokens per typical message. 15M Pro tokens buy roughly 6,666–16,685 messages.

Use Sonar from the API

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": "perplexity/sonar",
    "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="perplexity/sonar",
    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: "perplexity/sonar",
  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.

Full API docs → · Get an API key →

Frequently asked — Sonar

What is Sonar?

Sonar is a chat/completion model served by Perplexity and accessed through Faceb.ai. Try it without signing up — guest users get a small pool of session tokens to experiment.

Is Sonar free on Faceb.ai?

You get 30,000 tokens free every day — usually enough for a handful of messages a day on this model. Need more? Pro is $14.99/month for 15M tokens, or top-ups from $5.

What's Sonar's context window?

127,072 tokens. Paste your source material in, no need to truncate.

Can I call Sonar from the API?

Yes. Any API key from /account/api/ works with model slug `perplexity/sonar`. The OpenAI SDK works with base_url=https://api.faceb.ai/v1.

How does Sonar compare to GPT-4o or Claude?

Depends on the task. Faceb.ai lets you switch models per message — benchmark side-by-side by asking both the same prompt, which is more reliable than abstract comparisons.

How much does Sonar cost per message here?

Around 899–2,250 tokens per typical message. 15M Pro tokens buy roughly 6,666–16,685 messages.

Does Faceb.ai train on my Sonar prompts?

No. We contractually request that upstream providers not train on content routed through us. Your chat history lives only on your account.

Is Sonar good for coding?

It depends on the model size and training mix. For serious code work the developer favourites are Claude 3.5 Sonnet and DeepSeek V3; for quick edits, most capable models work fine.

Can I use Sonar on the API with the OpenAI SDK?

Yes — point your SDK at https://api.faceb.ai/v1 and use this model's slug as the model parameter. Everything else works as normal.

Does Sonar support image inputs?

Check the model catalog — multimodal models are marked in the picker. If it accepts images, you can drop screenshots and diagrams straight into the chat.

Can I switch from Sonar to another model mid-chat?

Yes — the picker is always at the top of the chat. Previous context carries over.

Will newer versions of Sonar show up here automatically?

Yes. Our catalog auto-fetches from the upstream aggregator, so provider updates and new versions appear in the picker as soon as they're available.

Or try a different model

Your Faceb.ai tokens work for every model — switch per message, no extra subscriptions.

Ready to chat?

One subscription covers every frontier model — switch between them per message. No extra API keys, no extra bills.

Start chatting with Sonar → Go Pro · $14.99/mo