Exa 3.0 beats Perplexity on 8 benchmarks and slashes search costs. Exa 3.0 claims the top spot on eight search benchmarks and introduces a cheaper Lite tier at $4 per 1,000 requests. · 3 hrs ago Read 4 min * Exa 3.0 launches as the company's largest search quality jump, claiming #1 on all eight tested benchmarks. * New Exa Lite tier priced at $4 per 1,000 requests, with Exa Auto at $7 per 1,000. * Dynamic Highlights now generally available, using 95% fewer tokens than full page text. * Index expanded with 1.27B ecommerce listings, 211M+ local businesses, flights, sports, weather, and transit data. * Reported scores include 91.8% on BrowseComp and 88.2% on DSQA, beating Perplexity, Brave, and Parallel. * Available today via the API, with upgrades applied automatically to existing integrations. Exa, a web search API for applications and AI agents, has released Exa 3.0, which the company describes as its largest search-quality upgrade to date. The release combines a larger embedding model, more efficient result highlights, billions of additional documents, and Exa Lite, a lower-cost tier for high-volume workloads. These changes affect relevance, context-window usage, data coverage, and API costs. Three upgrades reshape retrieval. Exa attributes the reported gains to three changes that apply across its search modes: * A larger embedding model: Exa trained it with more data and compute than any of its previous models. Embeddings represent queries and documents as numerical vectors, allowing the system to retrieve pages with related meaning even when their wording differs. * Dynamic Highlights: The feature is now generally available and selects relevant text across the complete result set. Exa says it uses 95% fewer tokens than sending full-page text while improving answer quality. * A broader index: Billions of documents now cover products, local businesses, flights, events, sports, weather, and other frequently changing subjects. Highlights allocate context across results. Dynamic Highlights changes how Exa extracts text for downstream models. Conventional retrieval pipelines often select passages from each page independently, producing repeated facts when several sources cover the same topic. Exa's model evaluates all returned pages together, allocates more tokens to stronger sources, and removes redundant material. For retrieval-augmented generation and agent workflows, smaller excerpts can reduce prompt size, model latency, and token charges. Cross-result selection can also fit a broader set of evidence into a fixed context window. Eight benchmark leads, according to Exa. Exa reports first-place results across eight public and domain-specific evaluations, including coding, finance, company research, and people search. Its published scores place Exa 3.0 ahead of the compared offerings from Perplexity, Brave, and Parallel. Exa 3.0 benchmark results reported by Exa | Benchmark | Reported score | | BrowseComp | 91.8% | | DSQA | 88.2% | | WideSearch | 56.1% | | ATLAS | 42.0% | | WebCode | 75.5% | | FinSearchComp | 68.0% | | Company FindAll | 15.4 | | People FindAll | 7.6 | The benchmarks use different tasks and scoring scales, so each row supports comparisons only within its evaluation. Exa published these results; teams considering a switch should also test representative queries from their own workloads. Lite shares the index and trims compute. Exa Lite and Exa Auto search the same underlying index. Auto spends more compute on candidate generation, which creates the initial pool of possible results, as well as highlight extraction and final ranking. Exa includes the upgraded highlights and expanded data sources in both tiers without an added fee. Exa search pricing and published agentic-search results | Tier | Price per 1,000 requests | Agentic-search score | Benchmark cost per task | | Exa Lite | $4 | About 79 | About $0.045 | | Exa Auto | $7 | About 80.5 | About $0.065 | The index moves into daily tasks. Exa says its crawler tracks more than 2 trillion URLs and its search infrastructure serves 100 billion pages. The latest expansion grew around customer query patterns, with traffic from personal AI assistants driving demand for commerce, local, travel, and real-time information. New and expanded index coverage | Category | Coverage | | E-commerce | 1.27 billion listings with prices and availability | | Local businesses | More than 211 million listings with hours and ratings | | Live information | News, sports, weather, and market data | | Travel and media | Flights, local events, transit, and podcasts | Product, place, and real-time data let one agent search for research papers, check store inventory, find a flight, or retrieve local business hours through the same provider. The expansion moves Exa beyond the long-form web content that established its neural-search product and into workloads often handled by general search or specialized data APIs. Route requests by the cost of a miss. * Choose Exa Lite for autocomplete, background enrichment, broad discovery, and large batch jobs where request volume dominates the cost calculation. * Choose Exa Auto for deep-research agents, coding assistants retrieving documentation, financial analysis, and user-facing answers where stronger ranking can justify the higher request price. Applications with mixed workloads can assign the higher-compute tier to queries where a missing or poorly ranked source carries greater operational cost, while sending routine searches through Lite. Existing pipelines change automatically. Exa 3.0, Dynamic Highlights, the expanded index, and Exa Lite are available through the API documentation. Existing integrations receive the retrieval and highlight upgrades automatically, so their request schemas require no migration. Existing integrations may still return different rankings and extracted passages after the rollout. Teams that maintain relevance tests, latency targets, prompt budgets, or cached results should rerun those checks against representative production queries.

Exa ranks #1 on the Artificial Analysis Search Index. Oct 19, 2026 The Artificial Analysis Search Index is a leading independent benchmark for search providers. Exa 3.0 ranks #1 for quality, while requiring the fewest search queries per task. Exa 3.0 introduced improvements across the retrieval stack including: * Training a larger embedding model with more compute and data than any previous model. * Making Dynamic Highlights generally available, using 95% fewer tokens than full page text while improving answer quality. * Adding billions of documents to its index across useful data types like products, local businesses, flights, events, sports, weather, and more. Exa's high-quality results let agents do 20% to 50% fewer search queries per task than other providers, while achieving higher accuracy. Budget options like DeepSeek Search end up needing 1.5x more queries than Exa, which eats away at any cost gains they might have. Read Artificial Analysis' full report to see more results and details on their evaluation methodology. Get started with Exa in the API dashboard or read the docs.

Introducing Exa 3.0. Oct 19, 2026 Today Exa is introducing Exa 3.0, the largest improvement to search quality Exa has ever released. It ranks first on every benchmark Exa tested, from public evaluations to coding, finance, and go-to-market intelligence. Exa is also launching Exa Lite, a new search type at $4 per 1,000 requests, built for cost-sensitive applications. Retrieval improvements. Exa 3.0 leads on evaluations spanning coding, finance, deep research, and company intelligence. The gains come from three improvements to its retrieval stack, and every search type benefits from them: * Trained a larger embedding model with more compute and data than any previous model. * Made Dynamic Highlights generally available, using 95% fewer tokens than full page text while improving answer quality. * Added billions of documents to its index across useful data types like products, local businesses, flights, events, sports, weather, and more. Exa Lite. Exa 3.0 also includes Exa Lite, its new search type, priced at $4 per 1,000 requests. Lite runs on the same index as Exa Auto. For higher quality, Exa Auto uses more compute across the retrieval stack, including candidate generation, highlights, and ranking. For cost-sensitive applications, Lite offers strong search quality at a lower price. Together, Lite and Auto set a new Pareto frontier for search. Better highlights, fewer tokens. Earlier this year, Exa released a research preview of Dynamic Highlights. With Exa 3.0, Dynamic Highlights is generally available at no additional charge. Improvements to model efficiency have made it substantially faster and cheaper to run. Instead of extracting highlights from each page, its new model selects tokens across all results, giving more to the best pages, cutting repeated information, and using 95% fewer tokens than full page text. Expanding its index. Exa runs its own crawler and an independent index. It tracks over 2 trillion URLs, serves 100 billion pages, and grows around what its customers search for. Exa has seen an explosion in usage from personal AI assistants, so Exa prioritized expanding its index and data partnerships to serve these use cases. Exa now includes: * 1.27B ecommerce listings with prices and availability * 211M+ local businesses with hours and ratings * Real-time news, sports, weather, and market data * Flights, local events, transit, and podcasts This new data adds to the coverage its customers already rely on, including people, companies, code, and publications. Availability. Exa 3.0 is available today through the API, including Exa Lite, upgraded highlights, and its expanded index. Exa Lite costs $4 per 1,000 requests, Exa Auto is $7 per 1,000 requests, and the improved highlights and expanded data sources are included at no additional charge. Join its Head of Product Shyam Kumar and Head of R&D Liam Hinzman for a live Exa 3.0 Q&A on Wednesday, October 21 at 1pm PT.