YepAPI

Command Palette

Search for a command to run...

PerplexityText Generation/v1/ai/chat

Sonar

Access Sonar through one API key. Affordable search-augmented AI with citations.

Perplexity's fast search-augmented model. Grounded answers with citations at a budget-friendly price. Great for high-volume research tasks.

No credit card required. Takes 30 seconds.

2,400+

Developers

1.2M+

API calls served

100+

Endpoints

$0.01

Per call

Yep, that's it.

Try it live

Send a message and see Sonar respond in real time.

POST/v1/ai/chat

Maximum tokens in the response.

Real-time tokens

Hit "Send Request" to see the response

Context Window

200K tokens

Max Output

8K tokens

Input Price

$1.40 / 1M tokens

Output Price

$1.40 / 1M tokens

Strengths

Search-augmented answers

Perplexity's fast model answers by searching the live web, grounding responses in current information rather than static training data.

Citations included

Responses come with citations and source links, so answers stay verifiable and traceable even at this budget price point.

Budget-friendly

At a flat $1.40 / $1.40 per 1M tokens it is far cheaper than Sonar Pro, built for high-volume grounded lookups, with a 200K-token context window.

Fast responses

Optimized for low latency, suited to interactive search-style answers and high-throughput research where speed matters, with up to 8,192 output tokens.

Quick start

Copy this snippet and start making calls with Sonar.

const res = await fetch('https://api.yepapi.com/v1/ai/chat', {
  method: 'POST',
  headers: {
    'x-api-key': 'YOUR_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    "model": "perplexity/sonar",
    "messages": [
      {
        "role": "user",
        "content": "Explain API gateways in 2 sentences."
      }
    ],
    "maxTokens": 256
  }),
});
const { data } = await res.json();
console.log(data.message.content);

Why use Sonar through YepAPI?

One API key for all models — no separate accounts
OpenAI SDK compatible — just change the base URL
No monthly minimums — pay per token
Switch models with one line of code
Full provider passthrough — citations, search results, and all extras included
Streaming and non-streaming support on every model
Works with Cursor, Claude, LangChain, and any LLM tool
Unified billing across all providers

Sonar API — pricing, context window & access

Sonar is Perplexity's fast, budget-friendly search-augmented model. It answers by searching the live web and returns citations with every response, at a flat low rate. It carries a 200K-token context window and up to 8,192 output tokens, built for high-volume grounded lookups.

Through YepAPI you reach Sonar over an OpenAI-compatible endpoint with one key that also covers the premium Sonar Pro, Claude, Gemini, Grok, Qwen, and Mistral, plus dedicated SEO, SERP, and web-scraping endpoints.

What is Sonar?

Sonar is Perplexity's standard search-augmented model, the faster and cheaper counterpart to Sonar Pro. Like Pro, it searches the live web for each query and grounds its answer in what it finds, attaching citations — but it is tuned for speed and low cost rather than maximum depth. It has a 200,000-token context window and returns up to 8,192 output tokens. It is the right pick when you need fresh, cited answers at high volume and don't require Pro's deeper research quality.

Build with Sonar via YepAPI

Call Sonar through YepAPI's OpenAI-compatible /v1/ai/chat endpoint with the model set to sonar; responses include citation data. Existing OpenAI SDK code works after a base-URL and model-name change. Use Sonar for high-volume grounded queries and escalate the ones that need depth to Sonar Pro with a one-string switch. The same key also reaches Claude, Mistral, and YepAPI's SEO, SERP, and scraping APIs.

Sonar API pricing — $1.40 / $1.40 per 1M tokens

Sonar costs a flat $1.40 per 1M input tokens and $1.40 per 1M output tokens on YepAPI — identical rates in and out, well below Sonar Pro. That flat, low pricing makes it easy to budget for high-volume search workloads where you run many grounded lookups. For most everyday fact-finding it offers the same core benefit — live, cited answers — at a fraction of Pro's cost. Billing is per token with no minimums.

Sonar for high-volume grounded lookups

Sonar fits workloads that need many fresh, cited answers cheaply: in-app search assistants, news and price monitoring, bulk fact-checking, and research tools that run constant queries. Its live grounding and citations keep answers current and verifiable, while the flat low rate keeps high request volumes affordable. Pair it with YepAPI's SERP and scraping endpoints for research pipelines that need breadth without Pro-tier cost.

Try Sonar free

Sign up for $5 in free YepAPI credit, no card required. At Sonar's flat low rate that covers a large number of grounded, cited queries — enough to test it across your search workloads before committing to paid usage.

Start generating in 30 seconds

$5 free credit on signup. No credit card required. Pay per call.

What developers say

Switched from SerpAPI and cut our SERP costs by 80%. Same data quality, way simpler billing.

Marcus T.

SEO Platform Founder

One API key for AI models, SERP data, and web scraping. Saved us from managing 4 separate providers.

Priya S.

Full-Stack Developer

The $5 free credit let us prototype our entire rank tracking feature before committing. No other API does that.

Jake R.

Indie Hacker

Frequently asked questions

Perplexity's fast search-augmented model. Grounded answers with citations at a budget-friendly price. Great for high-volume research tasks.

Input tokens cost $1.40 per 1M tokens and output tokens cost $1.40 per 1M tokens through YepAPI. No monthly minimums — you only pay for what you use.

Sign up for a free API key, then send requests to the /v1/ai/chat endpoint.

Sonar supports a 200K token context window with up to 8K output tokens per request.

Ready to use Sonar?

$5 free credit on signup. No credit card required. Pay per call.

Explore more models