November 2026
Perplexity released pplx-decider-v1.3 and pplx-decider-flash-v1.3 models, which support a new locate question type for identifying string spans. The models maintain v1.2 pricing.
Also shipped Nov 20, 2026Perplexity in November 2026 →
Improvements on the pull request overview in public preview
GitHub updated the pull request overview page in public preview, introducing clearer merge status indicators, collapsible reviews and comments, and persistent branch visibility on smaller screens.
Cloudflare Images - View delivery analytics for hosted images
Cloudflare introduced an Images Analytics dashboard for Cloudflare Images, offering up to 30 days of delivery metric trends and SQL access via the cf sql query CLI tool.
Gemini Enterprise: Generally available third-party data stores
Gemini Enterprise has reached general availability for a wide range of third-party data stores, including integrations with platforms like Asana, GitLab, Hugging Face, and Stripe.
Supervised fine-tuning for Gemini 3.8 Flash is available in General Availability
Supervised fine-tuning, continuous tuning, and tuning checkpoints for Gemini 3.8 Flash are now generally available on us and eu multi-region endpoints.
Compact numbers and basic value formatting are generally available ( GA ) in the default Explore interface
Looker 26.20 introduces generally available compact number and value formatting in the Explore interface, allowing users to abbreviate large values and set display formats without custom strings.
Security advisory permissions are now generally available
GitHub has made security advisory permissions generally available, allowing organization owners to assign specific security-related roles to users without granting full administrative access.
More from Perplexity APIEvery Perplexity API release →
November 2026
Perplexity updated its API xhigh effort tier to use GPT-6.2 Sol without fallback models, replacing Claude Opus 5.5 and GPT-6.1 Sol fallbacks.
November 2026
Perplexity launched pplx-embed-v2-context-9b and pplx-embed-v2-context-0.6b models to generate embeddings for search queries, document chunks, and images via a unified API endpoint.
November 2026
Perplexity added support for google/gemini-4-hydrogen to its Agent API and removed older Gemini Flash models from documentation.
November 2026
Perplexity released pplx-decider-v1.3 and pplx-decider-flash-v1.3 decision models, introducing a locate question type that returns matching string spans with character offsets.
November 2026
The Perplexity API now supports automatic output-token limits, allowing users to omit max_output_tokens for generations up to 128,000 tokens. This default is available in the new 2026-11-11.0 model versions.
November 2026
Perplexity added support for `google/gemini-4-carbon` to the Agent API with introductory pricing of $2.00 per million input tokens and $10.00 per million output tokens.
November 2026
Perplexity added an ultra effort level option to its Agent API, designed for broad research and data-gathering tasks using Claude Opus 5.5, with support for background execution mode.
November 2026
Decisions API: URL fetching and page freshness Pass a page URL as state with mode: "web_grounding" to fetch its text before searching. The fetched text replaces the URL before search. The response returns the page in fetched_results and search evidence in search_results . Set max_staleness to the maximum page age in seconds since its last crawl.