Perplexity

# Perplexity > Perplexity API documentation for building with the Agent API, the default for web-grounded AI and multi-provider applications, plus Search, Embeddings, and Sonar APIs. ## Docs - [Cancel Agent Response](https://docs.perplexity.ai/api-reference/agent-cancel-post.md): 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 stat… - [Download Agent Response File](https://docs.perplexity.ai/api-reference/agent-file-content-get.md): 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… - [List Agent Response Files](https://docs.perplexity.ai/api-reference/agent-files-get.md): 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. - [Retrieve Agent Response](https://docs.perplexity.ai/api-reference/agent-get.md): 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. - [Create Agent Response](https://docs.perplexity.ai/api-reference/agent-post.md): Generate a response for the provided input with optional web search and reasoning. - [Get Async Chat Completion](https://docs.perplexity.ai/api-reference/async-sonar-api-request-get.md): Retrieve the response for a given asynchronous chat completion request. - [List Async Chat Completions](https://docs.perplexity.ai/api-reference/async-sonar-get.md): Retrieve a list of all asynchronous chat completion requests for a given user. - [Create Async Chat Completion](https://docs.perplexity.ai/api-reference/async-sonar-post.md): Submit an asynchronous chat completion request. - [Computer Usage Analytics](https://docs.perplexity.ai/api-reference/computer-analytics-usage-get.md): Returns your organization's Computer 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… - [Computer Usage Analytics per Member](https://docs.perplexity.ai/api-reference/computer-analytics-usage-v2-get.md): Returns your organization's Computer credit usage broken down per member, as daily buckets. Each day lists one row per member who used credits that day, keyed by email, with the same Model and Credit Source breakdown as v1. Uses the same organization analytics API key as v1. Only complete UTC days a… - [Create Contextualized Embeddings](https://docs.perplexity.ai/api-reference/contextualized-embeddings-post.md): Generate contextualized embeddings for document chunks. Chunks from the same document share context awareness, improving retrieval quality for document-based applications. - [Create Embeddings](https://docs.perplexity.ai/api-reference/embeddings-post.md): Generate embeddings for a list of texts. Use these embeddings for semantic search, clustering, and other machine learning applications. - [Create Chat Completion](https://docs.perplexity.ai/api-reference/gateway-chat-completions-post.md): Send a conversation to any Gateway model using the OpenAI Chat Completions schema. Set `stream: true` to receive server-sent events; add `stream_options: {"include_usage": true}` to get token usage in the final chunk. - [Create Message](https://docs.perplexity.ai/api-reference/gateway-messages-post.md): S […gekürzt]