Create Agent Response - Perplexity

2026-03-11 · Source: perplexity.ai via Google News · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering · Depth: Intermediate, short

Summary

The provided content outlines the API specification for creating an agent response via Perplexity AI's `v1/agent` endpoint. It details the `cURL` and `POST` request methods, including the required `Authorization` header with a Bearer token and a `Content-Type: application/json` header. The request body accepts an `input` field, which can be a string or an array of input items, along with optional parameters such as `instructions`, `language_preference`, `max_output_tokens`, `max_steps` (ranging from 1 to 10), `model` (e.g., "xai/grok-4-1"), `models` (a fallback chain of 1-5 models), `preset` ("fast-search", "pro-search"), `reasoning` effort, `response_format` (supporting `json_schema`), `stream` for SSE, and `tools` like `web_search` or `function_tool`. The response structure includes `created_at` (Unix timestamp), `id`, `model` used, `object` type ("response"), an `output` array containing messages and tool results, `status`, `error` details, and `usage` information covering input/output tokens and costs in USD.

Key takeaway

For AI Architects designing conversational agents or data pipelines, understanding Perplexity AI's `v1/agent` API is crucial. You should leverage the `models` fallback chain for robust model selection and utilize `response_format.json_schema` to ensure structured, validated outputs. This allows for predictable integration into downstream systems and better control over response generation, especially when dealing with varied input types or requiring specific data formats.

Key insights

Perplexity AI's agent API enables structured, customizable AI responses with detailed control over models and tools.

Principles

• API requests require Bearer token authorization.
• Model selection supports fallback chains and presets.
• Output can be structured via JSON schema.

Method

To create an agent response, send a POST request to `/v1/agent` with an input payload, specifying model, instructions, and optional tools. The API returns a JSON object with output content, status, and usage metrics.

In practice

• Use `models` array for model fallback.
• Set `response_format.type` to `json_schema` for structured output.
• Monitor `usage.cost` for API expenditure.

Topics

• Perplexity AI Agent API
• Agent Response Creation
• API Request Parameters
• Model Selection
• Tool Integration

Best for: AI Architect, AI Product Manager, Entrepreneur, AI Engineer, Software Engineer

Related on AIssential

• Give it vision - Perplexity — Perplexity's Agent API unifies access to diverse LLM providers and specialized tools through a single interface.
• Prompt the agent - Perplexity — Distinguish agent "instructions" (persistent rules) from "input" (turn-specific task) for precise control and grounded retrieval.
• Perplexity Is Just a Pipeline. Here’s How to Build Your Own, Private and Local — A trustworthy AI answer engine is a local, private pipeline of open-source components, enforced by strict citation prompting.
• Perplexity Just Built an AI That Does Everything — Perplexity Computer offers a fully hosted, easy-to-use AI agent with extensive integrations, simplifying complex automation.
• Perplexity Max Debuts Multi-AI Agent Tool — Perplexity's new agent tool unifies 19 AI models for complex workflows, targeting professionals with a multimodal strategy.
• Perplexity Just Launched Their Own OpenClaw — Autonomous AI agents are evolving to handle complex, long-horizon tasks within isolated, multi-model environments.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by perplexity.ai via Google News.