Sign inDownload

← All integrations

Perplexity AI

Your own API keyOther

Connect it in Quilt

Perplexity AI provides conversational AI models for generating human-like text responses

Uses your own API key. Composio asks for it once and keeps it; Quilt never sees it.

Reads on its own16

Agents use these right away.

  • Download Agent Response FileDownload a file delivered by an Agent response's share_file tool.
  • Evaluate DecisionsEvaluate named yes/no, choice, and score questions against shared content.
  • Get Agent ResponseRetrieve a stored Agent response as a JSON snapshot (GET /v1/agent/{id}).
  • Get Async Chat CompletionGet Async Chat Completion (GET /v1/async/sonar/{id}).
  • Get Member Usage AnalyticsGet organization Perplexity usage per member in daily UTC buckets.
  • Get Orchestrator ModelRetrieve one Orchestrator model by its full provider/model id.
  • Get SkillGet a skill's metadata by identifier, optionally at a specific revision.
  • Get Skill Download URLGet a short-lived URL to download a skill bundle as a ZIP, optionally for a specific revision; omit the revision to select the active revision.
  • Get Usage AnalyticsGet an organization's Perplexity Computer usage as a bucketed time series.
  • List Agent Response FilesList files an agent response delivered from its sandbox using share_file.
  • List Async Chat CompletionsList a page of legacy asynchronous Sonar chat completion requests for the authenticated user, including their statuses.
  • List ModelsList Models (GET /v1/models).
  • List Orchestrator ModelsList available Orchestrator API models sorted by id, with base token prices.
  • List Skill RevisionsList a skill's revisions, newest first.
  • List SkillsList skills in the authenticated Project, newest first.
  • Perplexity Search (Raw Results)Search the Web (POST /search).

Asks someone first12

Anything that sends, creates, changes or deletes waits for a person to approve it in the session’s chat.

  • Cancel Agent ResponseRequest cancellation of an existing durable agent response.
  • Create Async Chat CompletionCreate Async Chat Completion (POST /v1/async/sonar).
  • Create Chat CompletionGenerate a chat-compatible response from conversation messages, with optional search controls.
  • Create Contextualized EmbeddingsCreate Contextualized Embeddings (POST /v1/contextualizedembeddings).
  • CreateEmbeddingsGenerate vector embeddings for independent texts (queries, sentences, documents).
  • Create Orchestrator Chat CompletionCreate a non-streaming OpenAI-compatible chat completion using a cataloged Orchestrator model.
  • Create Orchestrator MessageCreate a non-streaming Anthropic-compatible message using an Orchestrator catalog model.
  • CreateOrchestratorResponseGenerate a non-streaming model response through the Perplexity Orchestrator using a creator/model-name catalog ID, input text or structured items, optional tools, and structured output settings.
  • Create SkillCreate a Project-owned skill from a ZIP bundle containing SKILL.md.
  • Delete SkillDelete a skill only if its current revision matches expected_revision.
  • Execute AgentCreate Agent Response (POST /v1/agent).
  • Update SkillUpload a new ZIP bundle as a revision of an existing Project-owned skill.