Perplexity Sonar Pro

파라미터

경로, 쿼리, 헤더 파라미터가 없습니다.

요청 본문

• modelstring필수

  허용 값: sonar · sonar-pro · sonar-reasoning-pro · sonar-deep-research

  The Sonar model to use.

• messagesobject[]필수

  A list of messages comprising the conversation so far.

• rolestring필수

  허용 값: system · user · assistant

  The role of the message author.

• contentstring필수

  The content of the message.

• max_tokensinteger선택

  The maximum number of tokens to generate in the response.

• temperaturenumber선택

  Sampling temperature between 0 and 2. Lower values make output more focused and deterministic.

• top_pnumber선택

  Nucleus sampling parameter. The model considers tokens with top_p probability mass.

• top_kinteger선택

  The number of tokens to keep for top-k filtering.

• streamboolean선택

  허용 값: false

  Only non-streaming JSON responses are covered by this public contract. Set false.

• search_contextstring선택

  허용 값: low · medium · high

  Controls how much search context to use. Affects per-request cost.

• frequency_penaltynumber선택

  Penalizes new tokens based on their existing frequency in the text so far. Positive values decrease the likelihood of repeating the same line verbatim.

• presence_penaltynumber선택

  Penalizes new tokens based on whether they appear in the text so far. Positive values increase the likelihood of talking about new topics.

• return_citationsboolean선택

  Whether to return citations and search results in the response.

• search_recency_filterstring선택

  허용 값: month · week · day · hour

  Filter search results by recency.

• search_domain_filterstring[]선택

  Limit search to specific domains.

curl -X POST "https://openapi.felo.ai/v1/beta/perplexity/sonar-pro" \
  -H "Authorization: Bearer $FELO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "<string>",
  "messages": [
    {}
  ],
  "max_tokens": 0,
  "temperature": 0,
  "top_p": 0,
  "top_k": 0,
  "stream": false,
  "search_context": "<string>"
}'

응답

{
  "id": "example-sonar-pro-completion",
  "model": "sonar-pro",
  "object": "chat.completion",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "no-cache requires validation before reuse; no-store prohibits storage. [1]"
      },
      "finish_reason": "stop"
    }
  ],
  "citations": [
    "https://www.rfc-editor.org/rfc/rfc9111.html"
  ],
  "search_results": [
    {
      "title": "HTTP Caching",
      "url": "https://www.rfc-editor.org/rfc/rfc9111.html"
    }
  ],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 40,
    "total_tokens": 65
  }
}