Skip to content
Changelog

Report a bug

Perplexity AI integration: operations for AI agents

Perplexity AI connects to Type.com as an integration. This page lists the 33 operations documented for Claude and Codex in Type.com: 19 read, 10 write, 4 destructive.

About Perplexity AI

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

Categories: Analytics & Data

How to connect Perplexity AI to Type.com

Connect
Access token
Access
Organization connection: one shared account for the workspace.

To add the connection, follow the steps in Space connections.

Documented operations

33 operations. Your connection's permissions determine which operations are available. API references describe the vendor surface; they do not expand your connection's credentials or access.

33 operations listed.

Sonar

  • Write

    Create Chat Completion

    Generate a chat completion response for the given conversation.

    POST /v1/sonar

Search

  • Read

    Search the Web

    Search the web and retrieve relevant web page contents.

    POST /search

Embeddings

  • Write

    Create Embeddings

    Generate embeddings for a list of texts. Use these embeddings for semantic search, clustering, and other machine learning applications.

    POST /v1/embeddings

Contextualizedembeddings

  • Write

    Create Contextualized Embeddings

    Generate contextualized embeddings for document chunks. Chunks from the same document share context awareness, improving retrieval quality for document-based applications.

    POST /v1/contextualizedembeddings

Async

  • Read

    Get Async Chat Completion

    Retrieve the response for a given asynchronous chat completion request.

    GET /v1/async/sonar/{api_request}

  • Read

    List Async Chat Completions

    Retrieve a list of all asynchronous chat completion requests for a given user.

    GET /v1/async/sonar

  • Write

    Create Async Chat Completion

    Submit an asynchronous chat completion request.

    POST /v1/async/sonar

Agent

  • Read

    Retrieve Agent Response

    Retrieve a response created earlier. Returns a JSON snapshot of the response. Only responses created with `store` omitted or `true` can be retrieved; `store: false` responses return a 404.

    GET /v1/agent/{id}

  • Read

    List Agent Response Files

    List the files a response produced in the sandbox and delivered with the `share_file` tool. Scoped to the authenticated account, which only ever sees its own files. File content is not returned inline; download it with the file content endpoint.

    GET /v1/agent/{id}/files

  • Read

    Download Agent Response File

    Download the raw bytes of a file the response delivered with the `share_file` tool. The `file_id` comes from the file list endpoint and is distinct from the response `id`. The response streams raw bytes, not JSON, with a `Content-Type` matching the file and a `Content-Disposition: attachment` header carrying the original filename.

    GET /v1/agent/{id}/files/{file_id}/content

  • Write

    Create Agent Response

    Generate a response for the provided input with optional web search and reasoning.

    POST /v1/agent

  • Destructive

    Cancel Agent Response

    Requests cancellation of response `{id}`. Acts on durable state, so it works for background runs that outlive the client connection. Cancellation is asynchronous: a `200` acknowledges the request (`status: cancelling`) and the run stops shortly after - poll `GET /v1/agent/{id}` for its terminal status. Cancelling a run that is already terminal returns `400`. Ownership is enforced server side; a cross-tenant or unknown id surfaces as `404`.

    POST /v1/agent/{id}/cancel

Models

  • Read

    List Models

    List the models available for the Agent API. Returns model identifiers that can be used with the `POST /v1/agent` endpoint. The response follows the OpenAI List Models format for compatibility with third-party tools.

    GET /v1/models

Analytics

  • Read

    Usage Analytics

    Returns your organization's Perplexity usage analytics as a bucketed time series for a single dataset. Requires an organization analytics API key, generated by an org admin from Settings → Organization → Computer in the Perplexity web app. Only complete UTC grid buckets are returned: start_time snaps down to its bucket, and the in-progress bucket is never included. Datasets differ in what they count: credits for credit_usage, queries for query_volume, distinct active members for daily_active_users, and thread counts for the rest. Buckets of daily_active_users are not additive — a member active on several days is counted once per day, so summing them is not the window's active-member count.

    GET /v1/analytics/computer/usage

  • Read

    Usage Analytics per Member

    Returns your organization's Perplexity usage broken down per member, as daily buckets. Each day lists one row per member with usage that day, keyed by email. credit_usage carries a Model breakdown and an optional legacy Credit Source breakdown, subject to the same availability rules as v1; query_volume carries Feature, Project and Comet. Read the available axes from categories rather than assuming paid/promo data is present. Uses the same organization analytics API key as v1. Only complete UTC days are returned; the in-progress day is never included.

    GET /v2/analytics/computer/usage

Skills

  • Read

    List skills

    Lists the skills in your Project, newest first.

    GET /v1/skills

  • Read

    Get a skill

    Returns a skill. Without `revision`, returns the active revision.

    GET /v1/skills/{skill_id}

  • Read

    List skill revisions

    Lists the revisions of a skill, newest first.

    GET /v1/skills/{skill_id}/revisions

  • Read

    Get a skill download URL

    Returns a short-lived URL to download the skill bundle as a zip. Without `revision`, returns the active revision.

    GET /v1/skills/{skill_id}/download

  • Write

    Create a skill

    Creates a skill from a zip bundle. The bundle must contain a `SKILL.md` that provides the skill name and description; those fields are read from the bundle, not from the request.

    POST /v1/skills

  • Write

    Add a skill revision

    Uploads a new zip bundle as a new revision of an existing skill. Pass the revision you expect to replace as the required `expected_revision`; the request fails with `409` if the skill has already moved past it, so the update cannot race a concurrent write. Name and description are re-read from the new bundle.

    PUT /v1/skills/{skill_id}

  • Destructive

    Delete a skill

    Deletes a skill. Pass the current revision as `expected_revision`; the delete fails with `409` if the skill has a newer revision, so a delete never races a concurrent update.

    DELETE /v1/skills/{skill_id}

Decisions

  • Write

    Answer questions

    Evaluate one or more named questions against the content in `state`. Mix `noul`, `choice`, and `score` questions in one request; the response returns one answer per question under the same name, plus the model name and token usage. Set `model` to `pplx-decider-v1.2` or `pplx-decider-flash-v1.2`, or to the alias `pplx-decider-latest` or `pplx-decider-flash-latest`; a missing or unknown model returns `400`. Send the key as `Authorization: Bearer <key>`; an `x-api-key` header is not read and returns `401`.

    POST /v1/decisions

Batches

  • Read

    List batches

    Lists your organization's batches, newest first.

    GET /v1/batches

  • Read

    Retrieve a batch

    GET /v1/batches/{batch_id}

    GET /v1/batches/{batch_id}

  • Read

    List files

    Lists your organization's files, both uploads and the output and error files batches write. Deleted and expired files are not listed.

    GET /v1/files

  • Read

    Retrieve a file

    GET /v1/files/{file_id}

    GET /v1/files/{file_id}

  • Read

    Download file content

    Streams the raw bytes of an input, output, or error file.

    GET /v1/files/{file_id}/content

  • Write

    Create a batch

    Creates a batch from an uploaded input file. The batch starts in `validating`. Send an `Idempotency-Key` header to make retries safe: a repeat with the same key returns the original batch. `output_expires_after` is not supported and is rejected with a 400; output and error files are kept 30 days.

    POST /v1/batches

  • Write

    Upload a file

    Uploads a JSONL batch input file, up to 50,000 lines and 200 MB. Every line is validated before the file is stored. Files expire after 30 days; `expires_after` is not supported and is rejected with a 400.

    POST /v1/files

  • Destructive

    Cancel a batch

    Moves the batch to `cancelling`; it becomes `cancelled` once running items stop. Completed items stay in the output file and are billed. Cancelling a cancelled or cancelling batch returns it unchanged.

    POST /v1/batches/{batch_id}/cancel

  • Destructive

    Delete a file

    Deletes a file. Batches already created from it are not affected.

    DELETE /v1/files/{file_id}

Public API

  • Read

    List audit events

    Returns the organization's audit events, newest first. Requires an **audit log API key** (scope `audit_logs:read`) created by an org admin under **Enterprise APIs → Audit API**; Sonar API keys are rejected with `403`. Without time parameters the endpoint covers the most recent 30 days; a single request can span at most 30 days. See the [Audit API guide](/docs/admin/audit-api) for key setup, pagination patterns, and event fields.

    GET /v1/admin/audit-events

Get started

  1. Open Space settings → Connections and search for Perplexity AI.
  2. Connect your account and add the connection to the Space.
  3. Ask for what you need in any thread in that Space.

See How connections work for access and permissions, or browse all integrations.