Perplexity

AI search and answer platform for developers.

Perplexity API Changelog Monitoring

Perplexity is an AI search and answer platform for developers, offering APIs for search, research, and cited responses. This Perplexity API Changelog Monitoring page helps teams track product changes quickly so they can keep integrations, internal tools, and customer-facing features aligned with the latest platform behavior.

Strong Perplexity API Changelog Monitoring helps teams catch model updates, API changes, deprecations, pricing adjustments, and new developer features before they create downstream issues. It also supports better release planning by giving engineering and product teams a shared view of what changed and what may require action.

The benefit of Perplexity API Changelog Monitoring is simple: your team gets a repeatable way to review updates, evaluate integration risk, and respond before upstream platform changes affect production systems. Perplexity API changelog and developer updates

Perplexity API down?

Perplexity API down? For live availability checks, refer to Perplexity's official status or support channels. This page is focused on Perplexity API Changelog Monitoring, helping you follow releases, feature announcements, and breaking changes that may affect your integration over time.

Recent changes

Showing the last 10 changes from this feed.

04-13-2026

April 2026

New Integration: n8n n8n now ships a native Perplexity node with full API coverage — Chat Completions, Agent, Search, and Embeddings — all configurable from the visual canvas. Models load dynamically from the API, so the dropdown always reflects the latest options. Start here: n8n Integration Guide New Integration: OpenClaw OpenClaw, the open-source terminal AI agent, now supports Perplexity Search API as a native web search provider. Configure your API key once and get structured search results (title, url, snippet) directly inside your terminal workflows. Start here: OpenClaw Integration Guide API Credits now available through the AWS Marketplace The Perplexity API Platform is now available as a SaaS listing on AWS Marketplace. Purchase API credits through your AWS account for consolidated billing, simplified procurement, and no separate vendor relationship. Start here: AWS Marketplace /v1/models Endpoint A new GET /v1/models endpoint lists all available Agent API models in OpenAI-compatible format. No authentication required, useful for dynamic model selection in your integrations.

Source

04-13-2026

March 2026

Agent API: New Third-Party Models The Agent API now supports additional third-party models including GPT-5.4, NVIDIA Nemotron, Claude Sonnet 4.6, and Gemini 3.1 Pro Preview — giving you more flexibility for tool-calling, structured outputs, and model fallback chains. Model Deprecations: Gemini 2.5 Flash & Gemini 2.5 Pro As of March 20, 2026, google/gemini-2.5-flash has been deprecated and removed from the API. google/gemini-2.5-pro followed on April 1, along with google/gemini-3-pro-preview. If you were using these models, we recommend switching to newer alternatives available in the Models reference. Agent API Endpoint: /v1/agent The canonical Agent API endpoint is now /v1/agent. The previous /v1/responses path continues to work as an alias for OpenAI compatibility, no migration is required.

Source

03-04-2026

February 2026

Agent API: Now Available We're excited to announce the general availability of the Agent API! Build autonomous agents with production-ready guidance on model behavior, output controls, and OpenAI-compatibility patterns to seamlessly integrate with your existing systems. Start here: Agent API Quickstart Embeddings API: Now Available We're thrilled to launch the Embeddings API with comprehensive guides for standard and contextualized embeddings, plus best practices for semantic search and retrieval workflows. Start here: Embeddings API Quickstart

Source

12-17-2025

December 2025

Model Deprecation: sonar-reasoning Removed As of December 15, 2025, the sonar-reasoning model has been deprecated and removed from the API. If you were using this model, we recommend migrating to sonar-reasoning-pro for enhanced multi-step reasoning capabilities with web search. New: Media Classifier for Intelligent Visual Content We're excited to introduce the Media Classifier — an intelligent system that automatically detects when your queries would benefit from visual content and includes relevant images or videos in responses. Key capabilities: Automatic detection: Analyzes queries to identify when visual content adds value Smart media selection: Intelligently chooses between images, videos, or both based on query type Context-aware: Perfect for educational content, geographic queries, processes, and demonstrations Configurable control: Enable/disable and override media types as needed Available exclusively with sonar-pro, the Media Classifier enhances responses for visual concepts, locations, step-by-step processes, and educational content. Learn more → Search API Enhancements We've made several improvements to the Search API: New max_tokens parameter: Control the maximum tokens extracted per page in search results. This gives you finer control over response size and costs. Learn more → last_updated_filter support: Filter search results by when content was last updated, in addition to publication date. Perfect for finding the most current information. Learn more → Vercel AI SDK Support: The Search API is now compatible with the Vercel AI SDK, allowing you to build with Perplexity in a framework-agnostic way. Learn more → Ecosystem & Community New community showcase: Perplexity Client — An Electron-based desktop application with advanced API parameter controls, custom spaces, and API debugging mode. Built by the community for developers who want fine-grained control over their Sonar interactions.

Source

12-17-2025

June 2025

New: Academic Filter for Scholarly Research We're excited to announce the release of our new academic filter feature, allowing you to tailor your searches specifically to academic and scholarly sources. By setting search_mode: "academic" in your API requests, you can now prioritize results from peer-reviewed papers, journal articles, and research publications. This feature is particularly valuable for: Students and researchers working on academic papers Professionals requiring scientifically accurate information Anyone seeking research-based answers instead of general web content The academic filter works seamlessly with other search parameters like search_context_size and date filters, giving you precise control over your research queries. Example: For detailed documentation and implementation examples, please see our Academic Filter Guide.

Source

12-17-2025

November 2025

Pro Search: Now Generally Available We're excited to announce the general availability of Pro Search for Sonar Pro! Pro Search enhances your queries with automated tool usage, enabling multi-step reasoning through intelligent tool orchestration. Key capabilities: Multi-step reasoning: The model automatically performs multiple web searches and fetches URL content to answer complex queries Real-time thought streaming: Watch the model's reasoning process as it works through your question Automatic classification: Use search_type: "auto" to let the system intelligently route queries based on complexity Built-in tools: Access web_search and fetch_url_content tools that the model uses automatically Learn more about Pro Search in our Pro Search Quickstart guide. MCP Server: One-Click Installation The Perplexity MCP Server now supports one-click installation for popular AI development environments: Cursor: Click to auto-configure the Perplexity MCP server VS Code: One-click setup via the VS Code MCP extension Claude Desktop & Claude Code: Easy JSON configuration The MCP server provides four powerful tools: perplexity_search, perplexity_ask, perplexity_research, and perplexity_reason — enabling AI assistants to access Perplexity's search and reasoning capabilities directly.

Source

12-17-2025

October 2025

Official Perplexity SDKs We're thrilled to announce the official Perplexity SDKs for Python and Typescript! These SDKs provide convenient, type-safe access to all Perplexity APIs with both synchronous and asynchronous clients. Installation: Features: Full type definitions for all request parameters and response fields Support for Sonar and Search APIs Streaming support with async iterators Automatic environment variable handling for API keys Get started with our SDK Quickstart Guide and explore the Sonar API Guide for detailed usage examples. Interactive Search API Playground Test Search API queries and parameters in real time with our new Interactive Playground — no API key required to get started. Experiment with filtering options, see response structures, and refine your queries before implementing them in code. New Search API Capabilities language_preference: Specify preferred languages for search results (available for sonar and sonar-pro) search_domain_filter: Filter results to specific domains for more targeted searches Date/time filters: Enhanced control over result freshness with publication and update filters Ecosystem & Community New community showcase: StarPlex — An AI-powered startup intelligence platform featuring an interactive 3D globe interface. Built with Sonar Pro, it helps entrepreneurs validate business ideas by mapping competitors, VCs, and market opportunities worldwide. Featured at recent hackathon events!

Source

09-25-2025

September 2025

New: API Key Rotation Mechanism We've introduced a comprehensive API key rotation system to enhance security and simplify key management for your applications. Key features: Seamless Rotation: Replace API keys without service interruption Automated Workflows: Set up automatic key rotation schedules Enhanced Security: Regularly refresh keys to minimize security risks Audit Trail: Track key usage and rotation history Zero Downtime: Smooth transitions between old and new keys How it works: Generate a new API key while keeping the old one active Update your applications to use the new key Deactivate the old key once migration is complete This is particularly valuable for production environments where continuous availability is critical, and for organizations with strict security compliance requirements. Best practices: Rotate keys every 30-90 days depending on your security requirements Use environment variables to manage keys in your applications Test key rotation in staging environments first Monitor key usage to ensure successful transitions Access key rotation features through your API Portal.

Source

08-07-2025

August 2025

API model deprecation notice Please note that as of August 1, 2025, R1-1776 will be removed from the available models. R1 has been a popular option for a while, but it hasn't kept pace with recent improvements and lacks support for newer features. To reduce engineering overhead and make room for more capable models, we're retiring it from the API. If you liked R1's strengths, we recommend switching to Sonar Pro Reasoning. It offers similar behavior with stronger overall performance.

Source

07-17-2025

July 2025

New: SEC Filings Filter for Financial Research We're excited to announce the release of our new SEC filings filter feature, allowing you to search specifically within SEC regulatory documents and filings. By setting search_domain: "sec" in your API requests, you can now focus your searches on official SEC documents, including 10-K reports, 10-Q quarterly reports, 8-K current reports, and other regulatory filings. This feature is particularly valuable for: Financial analysts researching company fundamentals Investment professionals conducting due diligence Compliance officers tracking regulatory changes Anyone requiring authoritative financial information directly from official sources The SEC filter works seamlessly with other search parameters like date filters and search context size, giving you precise control over your financial research queries. Example: For detailed documentation and implementation examples, please see our SEC Guide.

Source