Perplexity Sonar API

Perplexity's Perplexity Sonar, through an OpenAI-compatible API. Providers quote it on an open exchange, and each request goes to the offer with the lowest estimated charge that meets your rules.

Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send perplexity-sonar as the model.
Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.

Facts

Model name: perplexity-sonar
Maker: Perplexity
Context window: 919.3K tokens
Input price: $2.400 per million tokens
Output price: $2.400 per million tokens
Providers: 1 independent provider
Regions: global

Providers

EmpirioLabs AI: global, $2.400 input and $2.400 output per million tokens, $2.400 cache read per million tokens, $0.019 fee for each request, 919.3K tokens of context

Scores

HLE: 4.9, #204 of 273
GPQA: 47.1, #216 of 250
LiveCodeBench: 29.5, #88 of 130
MMLU-Pro: 68.9, #93 of 133

Scores: Artificial Analysis (https://artificialanalysis.ai/)

Request

curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "perplexity-sonar",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is Perplexity Sonar?: Perplexity Sonar is a model from Perplexity.
How much does Perplexity Sonar cost?: Offers now ask $2.400 per million input tokens and $2.400 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.
What is the context length of Perplexity Sonar?: The largest offer takes 919,327 input tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can Perplexity Sonar do?: Its providers list Documents, Vision, Text.
What inputs and outputs does Perplexity Sonar support?: Text · Files · Images → Text.
Which providers serve Perplexity Sonar?: 1 independent provider quote it now, with 1 offer. The table above ranks them by the cost of a typical job.
How do I call Perplexity Sonar?: Send "perplexity-sonar" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was Perplexity Sonar listed?: The exchange first listed it on 10/17/2026. This is not its release date.