Meta tags:
description=Search through billions of items for similar matches to any object, in milliseconds. It’s the next generation of search, an API call away.;

Headings (most frequently used words):

pinecone, your, building, give, agents, knowledge, cost, performance, at, any, scale, indexes, always, visible, how, works, what, teams, build, with, for, organization, start, knowledgeable, ai, today, secure, compliant, reliable, subscribe, to,

Text of the page (most frequently used words):
pinecone (13), the (11), your (9), scale (9), and (8), for (7), query (7), vector (6), start (6), search (6), #indexes (6), get (5), #building (5), index (5), agent (5), cache (5), dense (5), aws (5), what (4), read (4), database (4), ready (4), type (4), enterprise (4), p50 (4), per (4), any (4), record (4), metrics (4), claude (4), customer (3), pricing (3), knowledgeable (3), with (3), not (3), latency (3), results (3), vectors (3), namespaces (3), namespace (3), required (3), knowledge (3), already (3), time (3), build (3), data (3), fast (3), count (3), upsert (3), east (3), region (3), 611 (3), run (3), systems (2), inc (2), terms (2), contact (2), rag (2), status (2), resources (2), security (2), assistant (2), dedicated (2), products (2), subscribe (2), demo (2), create (2), free (2), you (2), slas (2), built (2), explore (2), without (2), speed (2), 31ms (2), one (2), separate (2), fleet (2), grows (2), each (2), needs (2), there (2), compiled (2), assembled (2), agents (2), use (2), p99 (2), all (2), size (2), automatic (2), 100ms (2), searchable (2), seconds (2), write (2), are (2), stay (2), list (2), fetch (2), delete (2), update (2), units (2), lower (2), configuration (2), imports (2), browser (2), connect (2), svc (2), host (2), entry_01kqjg0rtkr8sf2khy97xyqak9 (2), records (2), west (2), manage (2), quickstart (2), started (2), performance (2), terminal (2), estimate (2), cost (2), code (2), install (2), registered, trademark, san, francisco, cookie, preferences, cookies, privacy, website, legal, newsroom, careers, partners, about, company, case, studies, blog, learning, center, community, forum, integrations, documentation, nodes, first, then, pay, when, today, uptime, support, success, reliable, soc, hipaa, gdpr, iso, 27001, certified, compliant, encryption, rest, transit, sso, rbac, cmek, private, networking, secure, meet, compliance, requirements, bring, market, faster, organization, filters, 12ms, metadata, filtering, runs, inside, after, relevance, ranking, land, together, added, filtered, same, unfiltered, recommendations, single, handles, billions, maintains, recall, manual, intervention, semantic, billion, 400, qps, isolated, memory, every, teams, cases, improving, searched, parallel, holds, steady, regardless, consistent, continuously, rebalancing, algorithms, selected, upgraded, background, automatically, tuning, throughput, streaming, acknowledged, under, within, acknowledgment, fully, managed, writes, instantly, indexing, queries, whitepaper, how, works, architecture, storage, p95, request, requests, second, 12hrs, 4hrs, 15m, updated, less, than, minute, ago, longer, ranges, resolution, represented, local, timezone, a1b2c3d, 1777663501, 1777749901, corporation, last_hit_at, hit_count, expires_at, cached_at, _id, 9997, score, rus, top_k, rerank, filter, top, operation, cache_bench, test, vjxlb1i, aped, 4627, b74a, 024, 847, 211, user, profiles, 072, 418, 302, product, 536, dimensions, name, api, keys, inference, backups, app, monitor, from, clean, console, call, always, visible, passion, project, pipeline, see, full, workload, next, steps, restart, running, above, command, copy, plugin, view, docs, mcp, cli, gemini, codex, copilot, cursor, retrieval, accurate, costs, give, log, customers, dismiss, nexus, now, public, preview, announcement,

Text of the page (random words):
the vector database to build knowledgeable ai pinecone pinecone nexus is now in public preview read the announcement dismiss products enterprise customers resources pricing contact log in start for free build knowledgeable ai give agents knowledge fast retrieval accurate results lower costs start in seconds start building get a demo get started claude code cursor copilot codex gemini cli mcp view docs claude plugin install pinecone copy install run above command in terminal start claude code run claude or restart if already running run pinecone quickstart for next steps cost performance at any scale estimate the cost of your workload see full pricing i m building a rag pipeline for a passion project get an estimate your indexes always visible monitor performance explore your data and manage indexes from a clean fast console or stay in the terminal your call app pinecone io get started database quickstart indexes 3 backups assistant inference api keys manage indexes create index name status records region type dimensions s cache ready 55 611 aws us east 1 dense 1 536 product search ready 2 418 302 aws us west 2 dense 3 072 user profiles ready 847 211 aws eu west 1 dense 1 024 s cache record count 55 611 region aws us east 1 type dense host s cache vjxlb1i svc aped 4627 b74a connect browser metrics namespaces 4 imports configuration records upsert record namespace cache_bench test operation search by id id entry_01kqjg0rtkr8sf2khy97xyqak9 top k 10 filter rerank search search 10 results top_k 10 1 rus ⓘ 1 score 0 9997 _id entry_01kqjg0rtkr8sf2khy97xyqak9 cached_at 1777663501 expires_at 1777749901 hit_count 0 last_hit_at 0 query what is a corporation s cache record count 55 611 region aws us east 1 type dense host s cache a1b2c3d svc pinecone io connect browser metrics namespaces 4 imports configuration metrics all metrics are represented in your local timezone updated less than a minute ago longer time ranges use lower resolution 15m 4hrs 12hrs 1d 2d 1w read units write units requests per second query upsert update delete fetch list request latency query upsert update delete fetch list p50 p95 p99 storage size record count architecture how pinecone works read the whitepaper pinecone is a fully managed vector database built for ai writes are instantly searchable indexing is automatic and queries stay fast at any scale 01 write 100ms acknowledgment acknowledged in under 100ms searchable within seconds vector throughput streaming in 02 index automatic no tuning required algorithms selected per data size upgraded in the background automatically index continuously rebalancing 03 query consistent at any scale all data searched in parallel speed holds steady regardless of scale p99 latency improving with scale use cases what teams build with pinecone agents isolated memory for every agent at any scale one namespace per agent no separate indexes required as your fleet grows the knowledge each agent needs is already there compiled not assembled at query time one namespace per agent no separate indexes required as your fleet grows the knowledge each agent needs is already there compiled not assembled at query time 400 qps 1 7m namespaces search semantic search at billion vector scale a single index handles billions of vectors and maintains recall without manual intervention 31ms p50 at 1b vectors 31ms 1b vectors p50 recommendations filtered results at the same speed as unfiltered metadata filtering runs inside the query not after relevance and ranking land together without added latency 12ms p50 with filters enterprise building for your organization explore enterprise meet the compliance security and scale requirements to bring enterprise ai to market faster secure encryption at rest and in transit sso rbac cmek private networking compliant soc 2 type ii hipaa gdpr and iso 27001 certified reliable uptime slas support slas and dedicated customer success built in start building knowledgeable ai today create your first index for free then pay as you go when you re ready to scale start building get a demo subscribe to pinecone subscribe products vector database dedicated read nodes assistant documentation pricing security integrations resources community forum learning center blog customer case studies status what is a vector db what is rag company about partners careers newsroom contact legal customer terms website terms privacy cookies cookie preferences pinecone systems inc san francisco ca pinecone is a registered trademark of pinecone systems inc