Perplexity llms.txt

The actual file

Source Markdown

The saved llms.txt text, displayed as source. The file belongs to its publisher; the live endpoint may change.

Showing the first 18000 characters. Load the complete file to read the remainder.

# Perplexity

> Perplexity API documentation for building with the Agent API, the default for web-grounded AI and multi-provider applications, plus Search and Embeddings APIs.

- [Overview](https://docs.perplexity.ai/docs/getting-started/overview.md): Perplexity API Platform - build with the Orchestrator, Agent, Search, Embeddings, and Decisions APIs. Real-time, web-wide research and Q&A capabilities for your products.
- [Quickstart](https://docs.perplexity.ai/docs/getting-started/quickstart.md): Generate an API key and make your first call in < 3 minutes.
- [Pricing](https://docs.perplexity.ai/docs/getting-started/pricing.md): Understand Perplexity API pricing, model rates, request fees, billing setup, and rate-limit references.
- [Perplexity API MCP Server](https://docs.perplexity.ai/docs/getting-started/integrations/mcp-server.md): Connect AI assistants to Perplexity's search and reasoning capabilities using the Model Context Protocol (MCP).
- [Perplexity Computer MCP Server](https://docs.perplexity.ai/docs/getting-started/integrations/computer-mcp-server.md): Give AI assistants the ability to complete real-world tasks using Perplexity Computer through the Model Context Protocol (MCP).
- [Perplexity CLI](https://docs.perplexity.ai/docs/cli/overview.md): Install and use Perplexity's pplx command-line interface for web search and query-relevant page snippets from your terminal or coding agent.
- [Perplexity Orchestrator API](https://docs.perplexity.ai/docs/router/quickstart.md): Unified access to open-weight models through OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs, with your Perplexity API key.
- [Orchestrator Models & Pricing](https://docs.perplexity.ai/docs/router/models.md): The model catalog for the Perplexity Orchestrator API, with per-token pricing for Perplexity-hosted and third-party models.
- [Routing & Reliability](https://docs.perplexity.ai/docs/router/routing-and-reliability.md): How the Perplexity Orchestrator API routes requests across model deployments, and what happens automatically when a provider degrades or fails.
- [Agent API](https://docs.perplexity.ai/docs/agent-api/quickstart.md): The Agent API is a multi-provider, interoperable API specification for building LLM applications. Access models from multiple providers with integrated real-time web search, tool configuration, reasoning control, and token budgets—all through one unified interface.
- [Define the run](https://docs.perplexity.ai/docs/agent-api/building-agents/define-the-run.md): Configure the agent run: start from a preset, then customize the system prompt, the loop bound, and the model.
- [Prompt the agent](https://docs.perplexity.ai/docs/agent-api/building-agents/prompt-the-agent.md): Split the standing rules (the system prompt) from the question (input), and ground the run so the agent searches and answers on the right thing.
- [Give it tools](https://docs.perplexity.ai/docs/agent-api/building-agents/give-it-tools.md): Enable built-in tools and your own custom tools in the tools array, let the model decide when to call them, and read the results back from the response.
- [Run code](https://docs.perplexity.ai/docs/agent-api/building-agents/run-code.md): Give the agent a sandbox so it computes exact answers instead of estimating them, runs real code, and returns generated files.
- [Structure the output](https://docs.perplexity.ai/docs/agent-api/building-agents/shape-output.md): Force the model to return JSON your code can parse instead of prose you have to scrape.
- [Keep context](https://docs.perplexity.ai/docs/agent-api/building-agents/keep-context.md): Carry a conversation across turns by replaying it in the input array, so a follow-up understands what came before.
- [Agent API Models](https://docs.perplexity.ai/docs/agent-api/models.md): Compare Agent API models, token pricing, supported service tiers, and provider documentation.
- [Presets](https://docs.perplexity.ai/docs/agent-api/presets.md): Explore Perplexity's Agent API presets - pre-configured setups optimized for different use cases with specific models, search configs, and tool access.
- [Profiles](https://docs.perplexity.ai/docs/agent-api/profiles.md): Run an Agent API request with a reusable, versioned configuration that you save and manage.
- [Model Fallback](https://docs.perplexity.ai/docs/agent-api/model-fallback.md): Specify multiple models in a fallback chain for higher availability and automatic failover.
- [Tools overview](https://docs.perplexity.ai/docs/agent-api/tools/overview.md): The tools an Agent API run can call - Perplexity-hosted built-in tools, remote MCP servers, and your own custom functions - and where to go for each.
- [Web Search](https://docs.perplexity.ai/docs/agent-api/tools/web-search.md): Search the web from the Agent API with filters, search configurations, pricing, parameters, and response fields.
- [Image Search](https://docs.perplexity.ai/docs/agent-api/tools/image-search.md): Search for web images from the Agent API with result limits, domain and format filters, typed results, streaming events, and per-invocation pricing.
- [Sandbox](https://docs.perplexity.ai/docs/agent-api/tools/sandbox.md): Execute code in isolated containers from inside an Agent API request.
- [Fetch URL Content](https://docs.perplexity.ai/docs/agent-api/tools/fetch-url-content.md): Fetch and extract content from specific URLs in the Agent API.
- [Finance Search](https://docs.perplexity.ai/docs/agent-api/tools/finance-search.md): Retrieve structured financial and market data in the Agent API.
- [People Search](https://docs.perplexity.ai/docs/agent-api/tools/people-search.md): Search for professionals, employees, and people using People Search in the Agent API
- [MCP](https://docs.perplexity.ai/docs/agent-api/tools/mcp.md): Connect a remote MCP server to an Agent API request and optionally approve tool calls before they run.
- [Connectors](https://docs.perplexity.ai/docs/agent-api/tools/connectors.md): Connect services or bring your own MCP server to your Project, then use them by connector ID in Agent API requests.
- [Custom Functions](https://docs.perplexity.ai/docs/agent-api/tools/custom-functions.md): Define a custom function, execute model-requested calls in your code, and return each result to the Agent API.
- [Output Control](https://docs.perplexity.ai/docs/agent-api/output-control.md): Streaming and structured outputs for the Agent API
- [Conversation state](https://docs.perplexity.ai/docs/agent-api/conversation-state.md): Continue an Agent API conversation across turns, either by replaying input yourself or by pointing at a completed prior response.
- [Image Attachments](https://docs.perplexity.ai/docs/agent-api/image-attachments.md): Learn how to upload and analyze images using base64 encoding or HTTPS URLs
- [Background Mode](https://docs.perplexity.ai/docs/agent-api/background-mode.md): Run long agentic tasks asynchronously — submit with background, poll by response id, stream, reconnect, and cancel.
- [Working with Files](https://docs.perplexity.ai/docs/agent-api/working-with-files.md): Send documents to the Agent API, continue a conversation about them, and download files produced by the agent.
- [Skills](https://docs.perplexity.ai/docs/agent-api/skills.md): Give the agent on-demand domain expertise with built-in, inline, and custom skills.
- [OpenAI Compatibility](https://docs.perplexity.ai/docs/agent-api/openai-compatibility.md): Use existing OpenAI SDKs with Perplexity's Agent API and understand the compatibility differences.
- [Migrate from Sonar to the Agent API](https://docs.perplexity.ai/docs/agent-api/migrate-from-sonar/overview.md): The Agent API represents a major upgrade of Sonar Chat Completions, bringing added configuration and powerful agentic primitives to your AI applications.
- [How to migrate from Sonar](https://docs.perplexity.ai/docs/agent-api/migrate-from-sonar/how-to.md): Move a Sonar chat completions integration to the Agent API, including requests, responses, search, presets, async runs, and parameter mappings.
- [Agent API vs Sonar benchmarks](https://docs.perplexity.ai/docs/agent-api/migrate-from-sonar/benchmarks.md): How Agent API presets perform against Sonar across the benchmarks we run, and which preset to use in place of each Sonar model.
- [Prompt Guide](https://docs.perplexity.ai/docs/agent-api/prompt-guide.md): How to write effective prompts for the Agent API.
- [Search API Overview](https://docs.perplexity.ai/docs/search/overview.md): The Search API returns ranked web results as JSON, not a generated answer. What each result contains, the request controls and limits, the price per request, and when to use it instead of the Agent API.
- [Perplexity Search API](https://docs.perplexity.ai/docs/search/quickstart.md): Access real-time web search results with Perplexity's Search API. Get ranked results, domain filtering, multi-query search, and content extraction for developers.
- [Fast Search](https://docs.perplexity.ai/docs/search/fast-search.md): Use search_type fast on the Search API for lower-latency, lower-cost web results.
- [Best Practices](https://docs.perplexity.ai/docs/search/best-practices.md): Learn best practices for optimizing search queries and implementing efficient async patterns with Perplexity's Search API.
- [Use Search API with the Anthropic SDK](https://docs.perplexity.ai/docs/search/agent-sdks/anthropic.md): Register Perplexity's Search API as a tool inside the Anthropic Messages API and run the standard tool-use loop with Claude.
- [Use Search API with the OpenAI SDK](https://docs.perplexity.ai/docs/search/agent-sdks/openai.md): Register Perplexity's Search API as a function tool inside the OpenAI Responses API and run the standard tool-call loop with GPT models.
- [Use Search API with the Google Gemini SDK](https://docs.perplexity.ai/docs/search/agent-sdks/gemini.md): Register Perplexity's Search API as a function tool inside Google's google-genai SDK and run the tool-call loop with Gemini models.
- [Search Date and Time Filters](https://docs.perplexity.ai/docs/search/filters/date-time-filters.md)
- [Search Language Filter](https://docs.perplexity.ai/docs/search/filters/language-filter.md)
- [Search Domain Filter](https://docs.perplexity.ai/docs/search/filters/domain-filter.md)
- [People Search](https://docs.perplexity.ai/docs/search/filters/people-search.md)
- [Perplexity Search SDK](https://docs.perplexity.ai/docs/search-sdk/overview.md): An agents-first Python SDK that brings Perplexity's Search as Code approach to your applications: composable retrieval primitives that agents orchestrate in code.
- [Embeddings API](https://docs.perplexity.ai/docs/embeddings/quickstart.md): Generate high-quality text embeddings for semantic search, RAG, and machine learning applications.
- [Best Practices](https://docs.perplexity.ai/docs/embeddings/best-practices.md): Optimize your embeddings workflow with batch processing, caching, RAG patterns, and performance tips.
- [Standard Embeddings](https://docs.perplexity.ai/docs/embeddings/standard-embeddings.md): Generate embeddings for independent texts, search queries, and single sentences.
- [Contextualized Embeddings](https://docs.perplexity.ai/docs/embeddings/contextualized-embeddings.md): Generate document-aware embeddings for chunks that share context, improving retrieval quality for document-based applications.
- [Decisions API](https://docs.perplexity.ai/docs/decisions/quickstart.md): The Decisions API answers questions about your content with probabilities instead of text: yes or no, one of your options, or a level on your rubric.
- [Quickstart](https://docs.perplexity.ai/docs/sdk/overview.md): Learn how to use the official Perplexity SDKs for Python and TypeScript to access the Perplexity APIs with type safety and async support.
- [Configuration](https://docs.perplexity.ai/docs/sdk/configuration.md): Learn how to configure the Perplexity SDKs for retries, timeouts, proxies, and advanced HTTP client customization.
- [Error Handling](https://docs.perplexity.ai/docs/sdk/error-handling.md): Learn how to handle API errors gracefully with the Perplexity SDKs for Python and TypeScript.
- [Performance Optimization](https://docs.perplexity.ai/docs/sdk/performance.md): Learn how to optimize the Perplexity SDKs for high-throughput applications with async support, connection pooling, and raw response access.
- [Type Safety](https://docs.perplexity.ai/docs/sdk/type-safety.md): Learn how to leverage full TypeScript definitions and Python type hints with the Perplexity SDKs for better development experience and code safety.
- [Best Practices](https://docs.perplexity.ai/docs/sdk/best-practices.md): Learn best practices for using the Perplexity SDKs in production, including environment variables, rate limiting, security, and efficient request patterns.
- [Signing In to the API Portal](https://docs.perplexity.ai/docs/admin/signing-in.md): Sign in to the Perplexity API Portal with Google, Apple, single sign-on, or a passwordless email code.
- [Projects & Billing](https://docs.perplexity.ai/docs/getting-started/projects.md): Learn how to use the Perplexity API Portal to manage access, usage, billing, and team collaboration.
- [API Key Management](https://docs.perplexity.ai/docs/admin/api-key-management.md): Learn how to generate, revoke, and rotate API keys for secure access
- [Safety Identifiers](https://docs.perplexity.ai/docs/admin/safety-identifiers.md): Identify your end users so a policy violation blocks one user instead of your whole API organization.
- [Analytics API](https://docs.perplexity.ai/docs/admin/computer-analytics-api.md): Query your organization's Perplexity usage analytics programmatically with a free, org-scoped API key
- [Rate Limits & Usage Tiers](https://docs.perplexity.ai/docs/admin/rate-limits-usage-tiers.md)
- [AWS Marketplace](https://docs.perplexity.ai/docs/resources/aws-marketplace.md): Subscribe to the Perplexity API Platform through AWS Marketplace for consolidated billing and enterprise procurement.
- [Perplexity with AG2](https://docs.perplexity.ai/docs/getting-started/integrations/ag2.md): Understand how AG2's Perplexity tools use the Search API and Sonar Chat Completions during the Agent API migration.
- [Perplexity with Agno](https://docs.perplexity.ai/docs/getting-started/integrations/agno.md): Use Perplexity's Agent API through Agno's OpenAI Responses integration.
- [Perplexity MCP Server for Google Antigravity](https://docs.perplexity.ai/docs/getting-started/integrations/antigravity.md): Connect Google Antigravity to Perplexity's hosted MCP server with bearer API-key authentication.
- [Perplexity with AnythingLLM](https://docs.perplexity.ai/docs/getting-started/integrations/anythingllm.md): Use Perplexity as the LLM provider in AnythingLLM for grounded, citation-backed chat over your documents and workspaces.
- [Perplexity with CAMEL-AI](https://docs.perplexity.ai/docs/getting-started/integrations/camel.md): Use the Perplexity Search API as a tool inside CAMEL-AI multi-agent systems.
- [Perplexity with Claude Code](https://docs.perplexity.ai/docs/getting-started/integrations/claude-code.md): Use Perplexity inside Claude Code — call the API from project code with the official TypeScript SDK, use the OpenAI-compatible base URL, or wire up the hosted Perplexity Docs MCP for in-editor documentation lookup.
- [Perplexity with Composio](https://docs.perplexity.ai/docs/getting-started/integrations/composio.md): Expose Perplexity's Agent, Search, and Embeddings APIs as MCP tools or direct API actions for any AI agent framework via Composio.
- [Perplexity with Cursor](https://docs.perplexity.ai/docs/getting-started/integrations/cursor.md): Use Perplexity with Cursor by calling the Agent API from project code with the Perplexity or OpenAI SDK, or by adding a Perplexity MCP server.
- [Perplexity with Haystack](https://docs.perplexity.ai/docs/getting-started/integrations/haystack.md): Use Perplexity's Agent API, Embeddings API, and grounded Search API in Haystack pipelines.
- [Perplexity web search in Hermes](https://docs.perplexity.ai/docs/getting-started/integrations/hermes.md): Use free Fast Search by default in Hermes Agent, or configure standard Perplexity web search and page extraction with your API key.
- [Perplexity with LangChain](https://docs.perplexity.ai/docs/getting-started/integrations/langchain.md): Use Perplexity's Agent API from LangChain and LangGraph.
- [Perplexity with LiteLLM](https://docs.perplexity.ai/docs/getting-started/integrations/litellm.md): Use Perplexity's Agent API and presets through LiteLLM's unified interface — Python SDK and Proxy.
- [Perplexity with LiveKit Agents](https://docs.perplexity.ai/docs/getting-started/integrations/livekit.md): Use Perplexity's Agent API as the LLM brain of a LiveKit voice agent.
- [Perplexity with Mastra](https://docs.perplexity.ai/docs/getting-started/integrations/mastra.md): Use Perplexity's Agent API and the Search API in your Mastra agents and tools.
- [Perplexity with n8n](https://docs.perplexity.ai/docs/getting-started/integrations/n8n.md): Add real-time web search, AI agents, and embeddings to your n8n workflows using the native Perplexity node.
- [Perplexity with OpenClaw](https://docs.perplexity.ai/docs/getting-started/integrations/openclaw.md): Use Perplexity as an LLM provider and web search provider in OpenClaw.
- [Perplexity with OpenCode](https://docs.perplexity.ai/docs/getting-started/integrations/opencode.md): Use the Perplexity Agent API inside the OpenCode AI coding agent — one endpoint, every frontier model, one API key.
- [Perplexity with Pipedream](https://docs.perplexity.ai/docs/getting-started/integrations/pipedream.md): Wire Perplexity into Pipedream workflows alongside 3,000+ other apps — automate research, summarization, and grounded responses with code and no-code steps.
- [Perplexity on Stripe Projects](https://docs.perplexity.ai/docs/getting-started/integrations/str