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.

07-09-2026

July 2026

Agent API: New Models The Agent API added support for several new models this month, all with direct first-party token pricing. See the full list in the Agent API Models reference. GPT-5.6 Family The Agent API now supports openai/gpt-5.6-sol, openai/gpt-5.6-terra, and openai/gpt-5.6-luna, giving you access to the latest GPT-5.6 models. Grok 4.5 The Agent API now supports xai/grok-4.5, xAI's flagship coding and agentic model. Retired: Gemini 3.1 Flash Lite Preview google/gemini-3.1-flash-lite-preview has been retired: Google removed the underlying preview model from its API. Requests for this id now return a model not supported error. Use google/gemini-3.1-flash-lite instead — the stable successor at the same pricing. See the Agent API Models reference.

Source

07-09-2026

June 2026

Agent API: New Models The Agent API expanded model coverage this month, all with direct first-party token pricing. See the full list in the Agent API Models reference. Claude Sonnet 5 — anthropic/claude-sonnet-5, Anthropic's latest Sonnet model. GLM 5.2 — perplexity/glm-5.2, Z.AI's flagship reasoning model. Kimi K2.7 Code — perplexity/kimi-k2.7-code, Moonshot AI's coding and agentic model. Nemotron 3 Super — nvidia/nemotron-3-super-120b-a12b, NVIDIA's open-weight reasoning model.

Source

07-09-2026

May 2026

Agent API: New Models The Agent API added support for several new third-party models this month, all with direct first-party token pricing. See the full list in the Agent API Models reference. Claude Opus 4.8 — anthropic/claude-opus-4-8, Anthropic's flagship model. Gemini 3.5 Flash — google/gemini-3.5-flash, Google's fast multimodal model. Gemini 3.1 Flash Lite — google/gemini-3.1-flash-lite (and -preview), a cost-efficient option. Grok 4.3 and the Grok 4.20 family — xai/grok-4.3, xai/grok-4.20-non-reasoning, and xai/grok-4.20-multi-agent.

Source

07-08-2026

July 2026

Agent API: Grok 4.5 Support The Agent API now supports xai/grok-4.5, xAI's flagship coding and agentic model, with direct first-party token pricing. See the full list in the Agent API Models reference.

Source

05-06-2026

May 2026

Finance Search: Now Available The finance_search tool is now available in the Agent API. Pull structured financial and market data — quotes, financials, earnings, analyst estimates, segment KPIs, ETF constituents, and more — for public companies and instruments. The model decides which fields to fetch based on your prompt, so a single call can return valuation, earnings, and context together. Highlights: Quotes and pricing: Near-real-time prices, OHLCV ranges, pre-market and after-hours data Financials: Income statement, balance sheet, cash flow (quarterly and annual), key ratios Earnings: Last call transcript, filings, beat/miss history, guidance Coverage and market activity: Analyst estimates, top gainers/losers, ownership and corporate actions Recommended configurations: Presets for live quotes, single-company historical lookups, and multi-step cross-company research Start here: Finance Search

Source

04-27-2026

April 2026

Agent API: New Third-Party Models The Agent API now supports Claude Opus 4.7, GPT-5.5, and Grok 4.20 Reasoning — extending model choice for tool-calling, structured outputs, and fallback chains. See the full list in the Models reference. API Key Management: Security Upgrade We've upgraded API key management with a one-time reveal model: full token values are now returned only at the moment of creation and cannot be retrieved again from the console or any endpoint. This significantly reduces the blast radius of credential exposure and aligns with industry best practices. Always set a descriptive token_name so keys remain identifiable after creation, and rotate regularly. Start here: API Key Management 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

April 2026

Agent API: New Third-Party Models The Agent API now supports Claude Opus 4.7, GPT-5.5, and Grok 4.20 Reasoning — extending model choice for tool-calling, structured outputs, and fallback chains. See the full list in the Agent API Models reference. API Key Management: Security Upgrade We've upgraded API key management with a one-time reveal model: full token values are now returned only at the moment of creation and cannot be retrieved again from the console or any endpoint. This significantly reduces the blast radius of credential exposure and aligns with industry best practices. Always set a descriptive token_name so keys remain identifiable after creation, and rotate regularly. Start here: API Key Management 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 Agent API 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

01-14-2026

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