Perplexity

Perplexity 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...

Context window
127Ktokens
Max output
114Ktokens
Input
$1.00/ 1M
Output
$1.00/ 1M

Quick start

from openai import OpenAI

client = OpenAI(
    base_url="https://neurongate.net/v1",
    api_key="sk-ng-your-api-key",
)

completion = client.chat.completions.create(
    model="perplexity/sonar",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(completion.choices[0].message.content)

Cost

Example requestTokensCost
Short prompt1K in$0.001
Typical chat turn1K in · 500 out$0.0015
Document analysis10K in · 2K out$0.012
Long context100K in · 10K out$0.11
Estimated cost per request$0.0015

Prices in USD. Billed per token actually used, from a balance prepaid in USDT, USDC, ETH or BTC.

Frequently asked questions

What is Perplexity 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...

How much does Perplexity Sonar cost?

Perplexity Sonar is priced at $1 per 1 million input tokens and $1 per 1 million output tokens when accessed via NeuronGate. You pay per token — no subscriptions required. Top up with crypto (USDT, USDC, ETH, BTC).

Does Perplexity Sonar support streaming?

Yes, Perplexity Sonar supports streaming responses via NeuronGate's API. Use the standard "stream": true parameter in your request.

What is the context window of Perplexity Sonar?

Perplexity Sonar has a context window of 127K tokens (~95K words). Maximum output is 114K tokens.

Does Perplexity Sonar support function calling (tools)?

Perplexity Sonar does not currently support function calling / tool use.

How do I use Perplexity Sonar with NeuronGate?

Create a NeuronGate account, top up your balance with crypto, generate an API key, and use the model id perplexity/sonar in your requests. NeuronGate uses the OpenAI-compatible API format — set your base URL to https://neurongate.net/v1.