Add Perplexity AI to your AI agent
Perplexity AI provides conversational AI models for generating human-like text responses
- Things your agent can do in Perplexity AI
- 28
Things your AI can do in Perplexity AI
Your FormWise AI can handle any of these in Perplexity AI — on its own, without you needing to click a button.
Cancel Agent Response
Request cancellation of an existing durable agent response. A successful acknowledgement means cancellation was accepted, not that the run has stopped. Poll GET /v1/agent/{id} for its terminal status. An already terminal run returns HTTP 400; unknown or cross-account IDs return HTTP 404.
Create Async Chat Completion
Create Async Chat Completion (POST /v1/async/sonar). Submits an asynchronous chat completion request for long-running tasks. Returns immediately with a request ID that can be polled using the Get Async Chat Completion action. Only the 'sonar-deep-research' model is supported for async processing. Async jobs have a 7-day TTL. Deep research generates very long responses (10K-100K+ words) with exhaustive multi-source analysis. Use the idempotency_key to prevent duplicate submissions. Poll with Get Async Chat Completion using the returned request ID to retrieve results when status is COMPLETED.
Create Chat Completion
Sonar support ended 2026-09-27. Generate a chat-compatible response via Agent. Non-streaming requests using model/messages/max_tokens/temperature/top_p migrate to POST /v1/agent with the provider's Sonar-to-effort mapping. Requests with other legacy controls, tool-role messages, or streaming retain the provider's /v1/sonar compatibility route so existing callers keep their original request/response contract. Prefer Execute Agent for new integrations. Returns choices, citations, search results, and token usage in the existing chat-completion shape. Recency and date filters are mutually exclusive. The legacy stop parameter is not supported by the provider.
Create Contextualized Embeddings
Create Contextualized Embeddings (POST /v1/contextualizedembeddings). Generates document-aware embeddings where chunks from the same document share context. Unlike standard embeddings, these recognize sequential relationships within documents, improving retrieval quality. Models: pplx-embed-context-v1-0.6b (1024 dims) and pplx-embed-context-v1-4b (2560 dims). Both support Matryoshka dimension reduction and INT8/binary quantization.
CreateEmbeddings
Generate vector embeddings for independent texts (queries, sentences, documents). This action takes one or more input texts and generates vector embeddings using Perplexity AI's embedding models. Embeddings are useful for semantic search, similarity matching, and machine learning downstream tasks. Supported models: - pplx-embed-v1-0.6b: Smaller, faster model (1024 dimensions) - pplx-embed-v1-4b: Larger, more accurate model (2560 dimensions) The output embeddings are base64-encoded for efficient transmission. Use the dimensions parameter to reduce embedding size for faster processing when full precision is not required (Matryoshka representation).
Create Orchestrator Chat Completion
Create a non-streaming OpenAI-compatible chat completion using a cataloged Orchestrator model. Supports multimodal conversations, structured output, reasoning, caching and tool calls where the selected model supports them. Returns the completion and token accounting; stream=True is unsupported.
Create Orchestrator Message
Create a non-streaming Anthropic-compatible message using an Orchestrator catalog model. Supply conversation history and max_tokens; optionally configure tools, sampling, thinking, caching or structured output where the model supports them. Returns content blocks, stop information and usage. stream=True is unsupported.
CreateOrchestratorResponse
Generate 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. Returns the full Responses-compatible resource; stream=True is rejected.
Create Skill
Create a Project-owned skill from a ZIP bundle containing SKILL.md. The bundle supplies the skill name and description. Returns the skill ID and revision metadata for subsequent use, updates, or deletion. The provider may reject invalid bundles, oversized uploads, or a Project's skill limit.
Delete Skill
Delete a skill only if its current revision matches expected_revision. Obtain the skill identifier and current revision from create or list skills. A successful deletion returns an empty acknowledgement. A revision conflict returns HTTP 409; retrieve the current revision before deciding to retry.
Download Agent Response File
Download a file delivered by an Agent response's share_file tool. Use the response ID and a file ID obtained from its file list. Returns a downloadable file rather than JSON-decoded or text-decoded provider bytes.
Evaluate Decisions
Evaluate named yes/no, choice, and score questions against shared content. Returns typed answers, probabilities, confidence where applicable, and token usage. The state plus any single question must fit within 256K input tokens; the complete body must be under 32 MiB. This is a non-streaming operation.
Show 16 more things it can do
Execute Agent
Create Agent Response (POST /v1/agent). Orchestrates multi-step agentic workflows with built-in tools (web search, URL fetching, function calling, finance search, image search), reasoning, and multi-model support. Streaming is not supported by this action. At least one of 'model', 'models', or 'preset' must be provided. Available presets: 'fast-search', 'pro-search', 'deep-research'. The 'deep-research' preset generates very long responses (10K-100K+ words) with exhaustive multi-source analysis. Available models include Perplexity Sonar, OpenAI, Anthropic, Google, xAI, and NVIDIA models at direct provider rates. Use the List Models action to see available model identifiers.
Get Agent Response
Retrieve a stored Agent response as a JSON snapshot (GET /v1/agent/{id}). Poll this action for background responses until their status is terminal. Only responses created with store omitted or true can be retrieved. An unknown ID, a response owned by another account, or store=false produces HTTP 404.
Get Async Chat Completion
Get Async Chat Completion (GET /v1/async/sonar/{id}). Retrieves the result of an asynchronous chat completion request by its ID. Use this to poll for the result after creating an async job. The response includes the status and, when completed, the full completion.
Get Member Usage Analytics
Get organization Perplexity usage per member in daily UTC buckets. Requires a separate organization analytics API key (the same key as the v1 analytics API), not a standard inference API key. The Analytics API must be enabled for the organization. credit_usage includes Model and Credit Source; query_volume includes Feature, Project and Comet. Only complete UTC days are returned, never the in-progress day. Recent days may be absent while the analytics store syncs. Follow next_page with the same query to retrieve more member rows; the requested window may span at most 90 days.
Get Orchestrator Model
Retrieve one Orchestrator model by its full provider/model id. Returns model metadata and base input, output, and available cache token prices. A model unavailable on the Orchestrator API returns HTTP 404.
Get Skill
Get a skill's metadata by identifier, optionally at a specific revision. Without revision, returns the active revision. The returned latest_revision identifies the current latest revision even when an older revision is requested.
Get Skill Download URL
Get a short-lived URL to download a skill bundle as a zip. Omit revision to select the active revision. Returns the URL only; does not fetch the bundle or forward API credentials to the download URL.
Get Usage Analytics
Get an organization's Perplexity Computer usage as a bucketed time series. Requires a separate organization analytics API key, generated by an org admin in Perplexity Settings → Organization → Computer, rather than a standard API inference key. Supply that key through the existing API-key authentication. Only complete UTC-grid buckets are returned; the in-progress bucket is omitted. Counts represent credits for credit_usage, queries for query_volume, distinct active members for daily_active_users, and threads for other datasets. Daily active-user counts are not additive across days. Analytics must be enabled for the organization (otherwise HTTP 404); rate limits apply across its keys.
List Agent Response Files
List files an agent response delivered from its sandbox using share_file. Only the authenticated account's files are visible. Returns file metadata, not inline content; use the file content endpoint to download a file. An unknown response id or one owned by another account returns HTTP 404.
List Async Chat Completions
Deprecated by the provider on 2026-09-27: asynchronous Sonar is no longer supported. List Async Chat Completions (GET /v1/async/sonar). For new asynchronous work use Agent background mode and Get Agent Response with a response id. Agent retrieval is not a replacement for listing all legacy jobs. Retrieves a list of all asynchronous chat completion requests for the authenticated user. Use this to see the status of all your pending, completed, and failed async jobs.
List Models
List Models (GET /v1/models). Lists models available for the Agent API. Returns model identifiers that can be used with the Agent endpoint. The response follows the OpenAI List Models format for compatibility. This is a public endpoint that does not require authentication.
List Orchestrator Models
List available Orchestrator API models sorted by id, with base token prices. Requires a Perplexity API key. Prices are in USD per 1M tokens and include input, output, and available cache-write and effective cached-input rates. Use the returned full model ids with the Orchestrator API.
List Skill Revisions
List a skill's revisions, newest first. Supply a skill identifier returned by create or List Skills. Returns revision tokens and available name and creation metadata. Pass next_page_token as page_token to retrieve another page.
List Skills
List skills in the authenticated Project, newest first. Returns skill identifiers and available name, revision, and timestamp metadata. To retrieve another page, pass the returned next_page_token as page_token.
Perplexity Search (Raw Results)
Search the Web (POST /search). Returns raw, ranked web search results directly from Perplexity's index without LLM processing. Faster and cheaper than chat completions when you need raw results. Supports filtering by domain, date, language, country, and recency. Max 20 results per request. Important: search_recency_filter and date filters (search_after_date_filter, search_before_date_filter, last_updated_after_filter, last_updated_before_filter) are mutually exclusive. Use one or the other, not both.
Update Skill
Upload a new ZIP bundle as a revision of an existing Project-owned skill. Supply the current revision as expected_revision; a concurrent change causes HTTP 409 rather than overwriting it. Name and description are re-read from SKILL.md in the new bundle. Returns the updated skill and revision metadata.
Built for the way you actually work
No code, no engineers
Connect in a few clicks and start using your AI right away. If you can use the apps you already love, you can do this.
Sounds like you, not like a bot
Train your AI on your offer, your voice, and the way you actually talk to clients — it picks up where you leave off.
Plugs into the stack you already use
No need to rip out your CRM, your scheduler, or your email tool. Your AI works inside the apps running your business today.
Your data stays yours
Client conversations, lists, and credentials are scoped to your workspace. Nothing gets shared, sold, or used to train anyone else’s AI.
What you can do once Perplexity AI is connected
Onboard new clients without lifting a finger
When someone signs up, your AI greets them, sets up their next step in Perplexity AI, and keeps the momentum going — even at 2am.
Reply to leads in seconds, not days
Your AI watches Perplexity AI for new inquiries, answers questions in your voice, and books the call before they cool off.
Get your weekends back
Hand off the repetitive Perplexity AI work — follow-ups, reminders, updates, simple admin — and stop being the bottleneck in your own business.
How to connect Perplexity AI to your agent
- 1
Start using FormWise for free
Sign up in under a minute.
- 2
Find Perplexity AI in your connected apps
Inside FormWise, open Connectors and look for Perplexity AI.
- 3
Hit "Connect"
Click "Connect Perplexity AI" and log in like you normally would. We only ask for the permissions your AI actually needs.
- 4
Tell your AI what to do in Perplexity AI
Build a quick AI Agent (it's like writing instructions, not code), and pick the Perplexity AI actions you want your AI to handle.
- 5
Watch it run
Send it a real-world task and watch your AI take care of Perplexity AI for you. Tweak the wording until it feels just right.
Powered by the AI you already trust
Your Perplexity AI workflow runs on the same world-class AI used by ChatGPT, Claude, and Gemini. We handle the technical part — you just tell your AI what to do, in plain English.
- OpenAI
- Anthropic Claude
- Google Gemini
Questions other Perplexity AI users had before signing up
Do I need to know how to code?
Not even a little. If you can use Perplexity AI today, you can set this up. You'll connect Perplexity AI, tell your AI what it should help with, and you're live. The whole thing is built for coaches, course creators, agencies, and operators — not engineers.
Will my clients know they're talking to an AI?
Only if you want them to. Your FormWise AI is trained on your voice, your offer, and the way you actually communicate — so it sounds like a thoughtful team member, not a clunky chatbot. Most people can't tell.
Can I make it sound like me?
Yes. You can give your AI examples of how you write, the questions you usually ask new clients, the way you handle objections, and the language you use about your offer. The more you give it, the more it sounds like you wrote it.
What if I want to take over a conversation?
You're always in control. You can step in at any point, take over from your AI, or stop it from sending messages until you've reviewed them. Think of it as a teammate, not a replacement.
Is my client data safe?
Yes. Your Perplexity AI login and client information stay scoped to your workspace. We don't sell it, we don't share it, and we don't use your data to train anyone else's AI. You can disconnect Perplexity AI or delete everything any time.
What happens when Perplexity AI updates their app?
We handle it. When Perplexity AI adds new features or changes how something works, we update the integration in the background. You don't have to do anything — your AI just keeps working.
How fast can I actually get this running?
Most people are up and running the same day they sign up. Connecting Perplexity AI takes a few minutes. Teaching your AI to handle the work the way you'd want it done is the part worth slowing down for.
What is FormWise?
FormWise is the AI agent builder for coaches, course creators, and agencies. You connect the apps you already use — like Perplexity AI — train your AI on your offer and voice, and let it handle the work you've been doing manually: onboarding, follow-ups, support, admin. No code, no developers, no engineering team required.
Can I sell AI agents to my clients?
Yes. A lot of FormWise users build AI assistants and sell them as part of their offer — done-for-you AI setups, white-label assistants for client businesses, custom GPTs trained on a client's brand. You can charge a setup fee, a monthly retainer, or both.
Can I embed my AI on my website or in my course?
Yes. Every AI you build in FormWise can be embedded on your site, dropped into your course platform, or shared as a standalone link. Your clients and students just open it like any other web page — no app to download, no login hoops.
Do I need to know anything about AI to use this?
No. If you can describe what you want your AI to do in plain English — "greet new clients, ask these 3 questions, book them a call" — FormWise can build it. We handle the models, the prompts, the connections. You handle the part you already know: what your business actually needs.
About Perplexity AI on FormWise
Perplexity AI provides conversational AI models for generating human-like text responses
Connect Perplexity AI once and your FormWise AI gets 28 things it can do inside it. That means your AI can handle the Perplexity AI work in your business — the messages, the updates, the follow-ups, the admin — the way you would, just faster and around the clock.
You don't need to know how any of it works under the hood. We take care of keeping the connection alive, retrying if something fails, and making sure your data only ever moves where you tell it to.
New to Perplexity AI? Take a look at perplexity.ai.
More Artificial Intelligence integrations
DataRobot
DataRobot is a machine learning platform that automates model building, deployment, and monitoring, enabling organizations to derive predictive insights from large datasets
ElevenLabs
Create natural AI voices instantly in any language - perfect for video creators, developers, and businesses.
OpenWeb Ninja
OpenWeb Ninja provides native APIs for web search, AI answers, e-commerce, finance, jobs, maps, news, real estate, contact enrichment, traffic, and web scraping.
Griptape
Griptape is a comprehensive platform offering tools and frameworks for building, deploying, and scaling generative AI applications.
Hugging Face
Build, train and deploy state of the art models powered by the reference open source in machine learning.
OpenAI
Toolkit for OpenAI APIs: manage Assistants, Threads/Messages; upload/list/delete Files; list/retrieve Models (including vision/multimodal); and view fine-tune listings and events.
Stop doing the Perplexity AI work yourself
Hand it off to an AI assistant that sounds like you, works around the clock, and never forgets a follow-up. Free to start.