perplexityavailablesupports_reasoningsupports_web_search

Back to Model Explorer

PerplexityAvailable on AvalAI

sonar-reasoning API on AvalAI

perplexity/sonar-reasoning

sonar-reasoning is an AI model from Perplexity that is available through AvalAI's OpenAI-compatible API.

Open dashboardCompare

Price display scale

Input price$1.00 / 1M tokens

Output price$5.00 / 1M tokens

Context window128,000 tokens

Maximum output— tokens

Use sonar-reasoning with the AvalAI API

Keep the API key in an environment variable and send requests from server-side code.

Bash

curl https://api.avalai.ir/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $AVALAI_API_KEY" \
  -d '{"model": "perplexity/sonar-reasoning", "messages": [{"role": "user", "content": "Give a concise, practical solution."}]}'

Python

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AVALAI_API_KEY"],
    base_url="https://api.avalai.ir/v1",
)

response = client.chat.completions.create(
    model="perplexity/sonar-reasoning",
    messages=[{"role": "user", "content": "Give a concise, practical solution."}],
)

print(response.choices[0].message.content)

JavaScript

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.AVALAI_API_KEY,
  baseURL: "https://api.avalai.ir/v1",
});

const response = await client.chat.completions.create({
  model: "perplexity/sonar-reasoning",
  messages: [{ role: "user", content: "Give a concise, practical solution." }],
});

console.log(response.choices[0].message.content);

Create an API keyRead the quickstart

Capabilities and endpoints

• Reasoning
• Web search

sonar-reasoning rate limits

Tier	RPM	TPM
Basic	3	40,000
Tier 1	10	200,000
Tier 2	50	450,000
Tier 3	75	2,000,000
Tier 4	150	4,000,000
Tier 5	250	10,000,000

Related models

• Sonar Reasoning Pro
• Sonar Pro
• Sonar Deep Research
• Sonar

Frequently asked questions

What is the sonar-reasoning API on AvalAI?

Create an AvalAI API key and send the model ID perplexity/sonar-reasoning to one of the supported endpoints shown on this page.

How much does the sonar-reasoning API cost on AvalAI?

The sonar-reasoning API on AvalAI costs $1.00 per 1M input tokens and $5.00 per 1M output tokens.

What is the token cost for sonar-reasoning?

Current AvalAI pricing for sonar-reasoning is $1.00 / 1M tokens for input and $5.00 / 1M tokens for output.

What is the sonar-reasoning context window?

The recorded maximum input context for sonar-reasoning is 128,000 tokens.

What are the rate limits for sonar-reasoning on AvalAI?

On tier 5, sonar-reasoning on AvalAI supports up to 250 requests per minute and 10,000,000 tokens per minute.

What features does sonar-reasoning support on AvalAI?

sonar-reasoning on AvalAI supports Reasoning, Web search.

What account tier is required to use sonar-reasoning on AvalAI?

Calling sonar-reasoning on AvalAI requires the Basic tier (tier 0) or higher.

Third-party data and freshness

• Pricing, availability, endpoints, and rate limits: AvalAI structured data (authoritative)