Sonar API

Perplexity's 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 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: sonar
Maker: Perplexity
Context window: 128K tokens
Input price: $1.001 per million tokens
Output price: $1.001 per million tokens
Providers: 1 independent provider
Regions: us

Providers

Architect: us, $1.001 input and $1.001 output per million tokens, $1.001 cache read per million tokens, 128K 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": "sonar",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is Sonar?: Served by intent-router: each job goes to the cheapest healthy upstream for this model.
How much does Sonar cost?: Offers now ask $1.001 per million input tokens and $1.001 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 Sonar?: The largest offer takes 128,000 input tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can Sonar do?: Its providers list Vision, Reasoning effort, JSON object, JSON schema, Frequency penalty, Logit bias, Log probabilities, Min-p sampling, Presence penalty, Repetition penalty, Seed, Stop sequences, Top-k sampling, Top-p sampling, Text, Tools.
What inputs and outputs does Sonar support?: Text · Images → Text.
Which providers serve 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 Sonar?: Send "sonar" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was Sonar listed?: The exchange first listed it on 10/8/2026. This is not its release date.