Aident logoAident logo centerAident Loadout
Use CasesPricingDocs
ENStart Now
AppsPerplexityai ToolsPerplexityai Create Chat Completion
Perplexityai Tools

Perplexityai Create Chat Completion

Perplexity Sonar Chat Completions (POST /v1/sonar). Generates web-grounded conversational AI responses with citations. Supports multiple Sonar models optimized for different use cases: - sonar: Fast, cost-effective for simple queries - sonar-pro: Enhanced quality for complex que…

Write actionRisk level 2 of 5API key connection
Use Perplexityai Create Chat Completion

Pricing and limits

Aident logo

Product

Aident LoadoutAident Playbook EditorOpen-CUAK

About

AppsSkillsUse CasesDocsBlogPricingDownloadsPrivacy PolicyTerms of Service

Alternatives

vs Composiovs Zapier
llms.txtGet an AI summary of Aident LoadoutSummarize with ChatGPTSummarize with ClaudeSummarize with GeminiSummarize with Perplexity

© Aident Labs, 2024-2026

Pricing
Free
Unified payment
Not currently supported

Inputs

  • stop
    Stop sequence(s) to end generation. Note: the API may not support custom stop words for all models.
  • modelstring
    The Sonar model to use. 'sonar' for fast/cheap queries, 'sonar-pro' for complex queries, 'sonar-reasoning-pro' for chain-of-thought reasoning, 'sonar-deep-research' for exhaustive research (generates very long 10K+ word responses; prefer the async endpoint for this model).
  • top_pnumber
    Nucleus sampling threshold controlling cumulative probability of tokens.
  • streamboolean
    Whether to stream the response using server-sent events.
  • messagesarray
    Required
    A list of messages comprising the conversation. Each message has a role (system, user, assistant, tool) and content. Messages with 'tool' role must alternate with 'assistant' messages. Valid pattern: system -> user -> assistant -> tool -> user.
  • max_tokensinteger
    Maximum number of tokens to generate. Max 128000.
  • search_modestring
    Search mode. Options: 'web', 'academic', 'sec'.
  • stream_modestring
    Stream mode: 'full' (default) or 'concise'.
  • temperaturenumber
    Controls randomness. 0 is deterministic, up to 2 is more random.
  • return_imagesboolean
    Whether to include images in the response.
  • disable_searchboolean
    Whether to disable web search entirely.
  • response_formatobject
    Response format configuration.

Observable output

  • data
    Required
    Data from the action execution
  • errorstring
    Error if any occurred during the execution of the action
  • successfulboolean
    Required
    Whether or not the action execution was successful or not

Skills that use this Action

Related use cases

No verified related use cases are linked yet.

Official source

Provider source

Skills that use this Action

No published Skills explicitly reference this Action yet.