# Hot **URL:** https://community.perplexity.ai/hot.md?page=16 [Latest](https://community.perplexity.ai/latest.md) · [Categories](https://community.perplexity.ai/categories.md) · [Tags](https://community.perplexity.ai/tags.md) **Page:** 17 --- ## [Introducing Fast Search in the Perplexity Search API](https://community.perplexity.ai/t/introducing-fast-search-in-the-perplexity-search-api/6195)
**Author:** [@pplx-announcements](https://community.perplexity.ai/u/pplx-announcements)\ **Replies:** 0\ **Last updated:** [September 24, 2026, 6:43pm UTC](https://community.perplexity.ai/t/introducing-fast-search-in-the-perplexity-search-api/6195 "2026-09-24T18:43:16Z")
Fast Search runs on Photon, our new Rust-based retrieval and ranking service that we built with a small team of engineers and hundreds of agents. It returns 95% of search results in 230 ms or less. How we built Photon:… --- ## [Add a batch query endpoint to Sonar](https://community.perplexity.ai/t/add-a-batch-query-endpoint-to-sonar/6217)
**Author:** [@emfedsci](https://community.perplexity.ai/u/emfedsci)\ **Replies:** 0\ **Last updated:** [September 27, 2026, 1:52am UTC](https://community.perplexity.ai/t/add-a-batch-query-endpoint-to-sonar/6217 "2026-09-27T01:52:53Z")
What I’m requesting: A single API call that accepts an array of independent queries and returns an array of results — e.g. POST /sonar/batch with { “queries”: \[…\] } → { “results”: \[ { query, answer, citations }, … \] }, w… --- ## [Preserve AI-suggested follow-up prompts after the user begins typing](https://community.perplexity.ai/t/preserve-ai-suggested-follow-up-prompts-after-the-user-begins-typing/6225)
**Author:** [@Ross\_Dessert](https://community.perplexity.ai/u/Ross_Dessert)\ **Replies:** 0\ **Last updated:** [September 28, 2026, 12:03am UTC](https://community.perplexity.ai/t/preserve-ai-suggested-follow-up-prompts-after-the-user-begins-typing/6225 "2026-09-28T00:03:40Z")
Feature request: Preserve AI-suggested follow-up prompts after the user begins typing. Suggested prompts often contain useful, tailored next steps. Currently, they disappear as soon as the Perplexity starts composing a … --- ## [Perplexity search results format: Need option to Hide Computer After Searches](https://community.perplexity.ai/t/perplexity-search-results-format-need-option-to-hide-computer-after-searches/6232)
**Author:** [@Sclwood](https://community.perplexity.ai/u/Sclwood)\ **Replies:** 0\ **Last updated:** [September 28, 2026, 12:50pm UTC](https://community.perplexity.ai/t/perplexity-search-results-format-need-option-to-hide-computer-after-searches/6232 "2026-09-28T12:50:57Z")
After every search, Perplexity presents a one-click Computer option at the bottom of the results. It is easy to select accidentally, and once Computer starts, it may run until completion or consume available credits. Pl… --- ## [You can now build custom reusable agents in the Perplexity Agent API with Profiles, Skills, and managed connectors](https://community.perplexity.ai/t/you-can-now-build-custom-reusable-agents-in-the-perplexity-agent-api-with-profiles-skills-and-managed-connectors/6235)
**Author:** [@pplx-announcements](https://community.perplexity.ai/u/pplx-announcements)\ **Replies:** 0\ **Last updated:** [September 28, 2026, 7:54pm UTC](https://community.perplexity.ai/t/you-can-now-build-custom-reusable-agents-in-the-perplexity-agent-api-with-profiles-skills-and-managed-connectors/6235 "2026-09-28T19:54:42Z")
Configure an agent once in the API Portal and reuse it across applications and workflows. A Profile saves the agent’s model, instructions, tools, Skills, and managed connectors under one versioned ID. Read more about P… --- ## [We built a new way to train contextual embedding models, which encode each chunk of a document with the whole document in view](https://community.perplexity.ai/t/we-built-a-new-way-to-train-contextual-embedding-models-which-encode-each-chunk-of-a-document-with-the-whole-document-in-view/6248)
**Author:** [@pplx-announcements](https://community.perplexity.ai/u/pplx-announcements)\ **Replies:** 0\ **Last updated:** [September 30, 2026, 8:08pm UTC](https://community.perplexity.ai/t/we-built-a-new-way-to-train-contextual-embedding-models-which-encode-each-chunk-of-a-document-with-the-whole-document-in-view/6248 "2026-09-30T20:08:09Z")
pplx-embed-v2-context-9b-preview sets a new state of the art on ConTEB and turbopuffer’s new, privately held context-bench. --- ## [Starting new user costs](https://community.perplexity.ai/t/starting-new-user-costs/5088)
**Author:** [@kingkarlito](https://community.perplexity.ai/u/kingkarlito)\ **Replies:** 4\ **Last updated:** [October 7, 2026, 2:25pm UTC](https://community.perplexity.ai/t/starting-new-user-costs/5088 "2026-10-07T14:25:28Z")
why is there a $50 minimum to even start working with the api? i’m not even sure if this will be a good fit for my project and you want me to send you $50 before i can create a key to test functionality? sure bill me for… --- ## [Pplx-decider-v1.1-27b, our updated open weights multimodal decision model, is now available](https://community.perplexity.ai/t/pplx-decider-v1-1-27b-our-updated-open-weights-multimodal-decision-model-is-now-available/6286)
**Author:** [@pplx-announcements](https://community.perplexity.ai/u/pplx-announcements)\ **Replies:** 0\ **Last updated:** [October 6, 2026, 9:11pm UTC](https://community.perplexity.ai/t/pplx-decider-v1-1-27b-our-updated-open-weights-multimodal-decision-model-is-now-available/6286 "2026-10-06T21:11:41Z")
It scores the highest on the new Hugging Face Decision Index 0.3 benchmark. pplx-decider-v1.1-27b costs half as much as v1, at $0.02 per million input tokens. --- ## [We're releasing pplx-embed-v2-late, two late-interaction embedding models that retrieve text, images, and pages with a shared embedding space for cross-model querying](https://community.perplexity.ai/t/were-releasing-pplx-embed-v2-late-two-late-interaction-embedding-models-that-retrieve-text-images-and-pages-with-a-shared-embedding-space-for-cross-model-querying/6296)
**Author:** [@pplx-announcements](https://community.perplexity.ai/u/pplx-announcements)\ **Replies:** 0\ **Last updated:** [October 7, 2026, 4:30pm UTC](https://community.perplexity.ai/t/were-releasing-pplx-embed-v2-late-two-late-interaction-embedding-models-that-retrieve-text-images-and-pages-with-a-shared-embedding-space-for-cross-model-querying/6296 "2026-10-07T16:30:34Z")
Both models achieve frontier performance and are publicly available on Hugging Face. --- ## [Pplx-decider-v1.1-27b scores the highest on Decision Bench for accuracy, with the lowest cost](https://community.perplexity.ai/t/pplx-decider-v1-1-27b-scores-the-highest-on-decision-bench-for-accuracy-with-the-lowest-cost/6312)
**Author:** [@pplx-announcements](https://community.perplexity.ai/u/pplx-announcements)\ **Replies:** 0\ **Last updated:** [October 9, 2026, 4:27pm UTC](https://community.perplexity.ai/t/pplx-decider-v1-1-27b-scores-the-highest-on-decision-bench-for-accuracy-with-the-lowest-cost/6312 "2026-10-09T16:27:17Z")
It reached 94.5% accuracy across 1071 cases at $0.017 per 1,000 decisions. Full evaluation: https://decisionbench.ai Get Started: Decisions API - Perplexity --- ## [Agent API using credit](https://community.perplexity.ai/t/agent-api-using-credit/6331)
**Author:** [@api-triage-bot](https://community.perplexity.ai/u/api-triage-bot)\ **Replies:** 1\ **Last updated:** [October 12, 2026, 5:05pm UTC](https://community.perplexity.ai/t/agent-api-using-credit/6331 "2026-10-12T17:05:15Z")
Reported in Discord by @tech2hard — Discord I created new api key like 2 days back for testing decision api and it started using agent api and finished the credit in 1 day by using agent api. now there is no way to get … --- ## [Reg: Dashboard and Billing](https://community.perplexity.ai/t/reg-dashboard-and-billing/6343)
**Author:** [@sha](https://community.perplexity.ai/u/sha)\ **Replies:** 0\ **Last updated:** [October 12, 2026, 9:20pm UTC](https://community.perplexity.ai/t/reg-dashboard-and-billing/6343 "2026-10-12T21:20:13Z")
Pre-flight checklist This is a Perplexity API feature request, not a Perplexity app, Comet, or web UI request. I have checked whether this already exists in the docs or another forum topic. I have described the devel… --- ## [Decisions API returns near-uniform probabilities for every question, including the quickstart example](https://community.perplexity.ai/t/decisions-api-returns-near-uniform-probabilities-for-every-question-including-the-quickstart-example/6348)
**Author:** [@Urs\_de\_Swardt](https://community.perplexity.ai/u/Urs_de_Swardt)\ **Replies:** 2\ **Last updated:** [October 13, 2026, 4:33pm UTC](https://community.perplexity.ai/t/decisions-api-returns-near-uniform-probabilities-for-every-question-including-the-quickstart-example/6348 "2026-10-13T16:33:14Z")
Pre-flight checklist This is about the Perplexity API, not the Perplexity app, Computer, Comet, or web UI. I have removed API keys, secrets, and private data. I have included enough information for someone else to re… --- ## [Hack The Nest at EMU (Nov 14-15): who should I talk to about API credits for student hackers?](https://community.perplexity.ai/t/hack-the-nest-at-emu-nov-14-15-who-should-i-talk-to-about-api-credits-for-student-hackers/6307)
**Author:** [@Melvin\_Karupati](https://community.perplexity.ai/u/Melvin_Karupati)\ **Replies:** 3\ **Last updated:** [October 14, 2026, 5:55pm UTC](https://community.perplexity.ai/t/hack-the-nest-at-emu-nov-14-15-who-should-i-talk-to-about-api-credits-for-student-hackers/6307 "2026-10-14T17:55:23Z")
Hi all! I’m Melvin, Vice President of GDG on Campus at Eastern Michigan University and co-lead of Hack The Nest, EMU’s first hackathon. A moderator on the Perplexity Discord suggested I ask here. The event Nov 14-15, … [Previous page](https://community.perplexity.ai/hot.md?page=15)