# Perplexity updates Every Perplexity update in one feed — release notes, features and changes, straight from the source. 87 updates - ## [Perplexity Computer now works in your own Chrome]() A new extension links the Mac and Windows apps to sites you already use, and Comet still does not need it. 2026-10-30 - ## [Perplexity voice mode runs Computer sessions and Projects]() One voice session can span several Computer sessions, start tasks, and manage Projects. It is on the Mac app and the web for Pro and Max. 2026-10-28 - ## [Perplexity Computer adds the HyperFrames video skill]() HeyGen’s HyperFrames skill, now in Perplexity Computer’s skills marketplace, turns a written description of a video into a finished MP4. 2026-10-25 - ## [Perplexity Computer adds the Impeccable design review skill]() The Impeccable skill, now in Perplexity Computer’s skills marketplace, reviews an interface for layout, type, contrast and accessibility and fixes the issues. 2026-10-24 - ## [Perplexity Computer adds the Taste Skill for website art direction]() The Taste Skill in Perplexity Computer’s skills marketplace sets an art direction before Computer builds a site, drawing on 247 award-showcase websites. 2026-10-23 - ## [Perplexity Computer adds a PHP2Shell skill to check sites for exposure]() The new skill scans PHP sites and GitHub deployment configs for exposure and ranks the fixes. Runs are free through October 31. 2026-10-22 - ## [Perplexity Computer can now run fully local on your Mac]() Both the model and the agent now run on supported Apple silicon Macs, so Computer can work with your files and Mac apps without sending data to the cloud. 2026-10-20 - ## [Perplexity Computer adds interactive CAD previews]() Inspect a 3D preview, export editable CAD and review FreeCAD edits through a video of the changes. 2026-10-06 - ## [Perplexity Computer for Mac adds tabs and separate windows]() Version 26.37.1 supports parallel work across tabs, windows and screens for Computer Mac users. 2026-10-05 - ## [Perplexity demonstrates a browser game built in Light mode]() The vendor’s flight-game example used 97 credits; that is an example cost rather than a fixed price. 2026-10-05 - ## [Low, medium, and high presets use Fast Search]() Search calls on the affected presets now cost $1 per 1,000 invocations, plus model tokens, and run about 800 ms faster. 2026-10-01 - ## [New: Decisions API]() Any Perplexity API key works, with input priced at $0.04 per million tokens, free output tokens and no per-request fee. 2026-10-01 - ## [Native document input]() Developers can send five document formats inline or by public HTTPS URL, then ask follow-ups about inline files without uploading again. 2026-10-01 - ## [Image Search]() Developers can filter sources and formats in Agent API requests, with successful searches costing $2.50 per 1,000 calls. 2026-10-01 - ## [Accurate sandbox extraction usage and costs]() Successful sandbox extraction calls now count towards Agent API response totals, with pricing unchanged and no historical backfill. 2026-10-01 - ## [Claude Haiku 5.5]() Requests with up to 100,000 input tokens cost $0.10 per million input tokens, with higher rates above that threshold. 2026-10-01 - ## [Decisions API: pplx-decider-v1.1-27b replaces v1]() Input tokens now cost $0.02 per million, and requests using the previous model name continue to work at the lower rate. 2026-10-01 - ## [NVIDIA Nemotron 3.5 Super]() The Agent API adds a text-only reasoning model with a 1M-token context window, priced at $0.20 per million input tokens, replacing Nemotron 3 Ultra. 2026-10-01 - ## [Decisions API: pplx-decider-v1.2 and pplx-decider-flash-v1.2]() The 27B decider stays at $0.02 per million input tokens, and a new 4B flash model costs $0.01, with both accepting text and images. 2026-10-01 - ## [Gemini 4 Argon]() Gemini 4 Argon costs $2.00 per million input tokens and $10.00 per million output tokens through November 30, 2026, on default processing only. 2026-10-01 - ## [Older models removed from the model docs; GPT-6 Astra and DeepSeek V4 Pro added]() Perplexity's Agent API docs drop old Claude, Gemini and Grok models, and list GPT-6 Astra at $10 per million input tokens and DeepSeek V4 Pro at $1.32. 2026-10-01 - ## [Tool approvals for MCP and connector calls]() Developers can set require\_approval to "always" or a filter, then approve or deny each call; Python SDK 0.43.8 and TypeScript SDK 0.38.8 add the types. 2026-10-01 - ## [xhigh preset output budget raised to 512,000 tokens]() The Agent API preset now allows 512,000 output tokens, and frozen configurations need max\_output\_tokens updated to match. 2026-10-01 - ## [Low, medium, high, and xhigh presets use Fast Search]() Agent API web\_search calls under the low to xhigh presets now cost $1.00 per 1,000, down from $2.50, and run about 800 ms faster. 2026-10-01 - ## [DocSend Connector in Perplexity Computer]() Perplexity Computer can now pull DocSend deal room files to keep documents like investment theses current. 2026-09-24 - ## [GPT-6 Sol Arrives in Perplexity and Computer]() GPT-6 Sol is now Perplexity Computer's default Light-effort model, and is also available in Perplexity itself. 2026-09-22 - ## [Effort Mode, GPT-6 Astra, and Skills Marketplace]() Perplexity adds effort levels to Computer, opens a Skills Marketplace, and brings GPT-6 Astra to Pro and Max plans. 2026-09-21 - ## [Video Creation in Perplexity Computer]() Perplexity Computer adds AI video generation via MiniMax H3 and Seedance 2.5, available to Pro and Max subscribers. 2026-09-21 - ## [Portable Computer Comes to Windows RTX PCs]() The Windows feature keeps file and app work local on RTX hardware, while still allowing frontier cloud models when needed. 2026-09-14 - ## [Tag Coworkers in Computer Sessions]() Perplexity Computer adds @ mentions on the web, letting users tag and share sessions with coworkers. 2026-09-11 [Open Perplexity updates on Creators Toolbox]() --- Canonical source: https://creatorstoolbox.com/updates/perplexity