Perplexity AI for your agents.

What agents can do with Perplexity AI

Curated for agents: the calls that matter, with schemas and descriptions written for tool use, not an endpoint dump.

• perplexity_chat_completion

  Send a chat completion request. `model` is one of: sonar-pro, sonar, sonar-reasoning, sonar-reasoning-pro, codellama-70b. Perplexity models return grounded search results with citations.

• perplexity_list_models

  List available models.

• perplexity_search

  Perplexity Search API: run a raw web search and get ranked results (title, url, snippet) without an LLM answer. `query` is a string or array of queries.

• perplexity_async_chat_completion

  Submit a chat completion to run asynchronously (for long queries). `request` holds the standard {model, messages} payload. Returns a request id; poll get_async_chat_completion.

• perplexity_list_async_chat_completions

  List your async chat completion requests and their statuses.

• perplexity_get_async_chat_completion

  Fetch the status and (when finished) the result of one async chat completion by request id.

• perplexity_get_model

  Get details of a specific model.

• perplexity_create_embedding

  Create an embedding vector for text input.

• perplexity_cancel_async_chat

  Cancel a running async chat completion by request id.

• perplexity_get_usage

  Get API usage statistics for the current billing period.

• perplexity_text_completion

  Text completion (legacy non-chat). `prompt` is the input text.

Connect it in a minute

The connect flow is agent-driven: Even opens the key page in its own browser and collects the key through a secure native field. It never passes through the chat.

1. Paste the prompt below into any agent running inside Even, or click Connect in Even's catalog.
2. Sign in to Perplexity and go to the API settings page.
3. Click 'Generate API key' or copy an existing one.
4. Copy the key.
5. Paste the key into Even's secure field. Even verifies it and your agents are live.