The web, organized for agents

exa.ai · 2026-05-21 · by Long Nguyen ·generic
Real-time AI search engine with a powerful web search API, web crawling API, SERP API, and deep research tools. Search and extract structured content from websites and live data.

The web, organized for agents

Exa raises $250M Series CExa raises $250M Series C to build the search engine for AIs.Read more

github.com/zai-org/GLM-5

openlm.ai/kimi-k2.6

smbtech.au/news/google-deepmind-releases-gemma-4-its-most-capable-open-source-ai-models

github.com/HiDream-ai/HiDream-O1-Image

bentoml.com/blog/navigating-the-world-of-open-source-large-language-models

github.com/zai-org/GLM-5

openlm.ai/kimi-k2.6

smbtech.au/news/google-deepmind-releases-gemma-4-its-most-capable-open-source-ai-models

github.com/HiDream-ai/HiDream-O1-Image

bentoml.com/blog/navigating-the-world-of-open-source-large-language-models

github.com/zai-org/GLM-5

openlm.ai/kimi-k2.6

smbtech.au/news/google-deepmind-releases-gemma-4-its-most-capable-open-source-ai-models

github.com/HiDream-ai/HiDream-O1-Image

bentoml.com/blog/navigating-the-world-of-open-source-large-language-models

github.com/zai-org/GLM-5

openlm.ai/kimi-k2.6

smbtech.au/news/google-deepmind-releases-gemma-4-its-most-capable-open-source-ai-models

github.com/HiDream-ai/HiDream-O1-Image

bentoml.com/blog/navigating-the-world-of-open-source-large-language-models

github.com/zai-org/GLM-5

openlm.ai/kimi-k2.6

smbtech.au/news/google-deepmind-releases-gemma-4-its-most-capable-open-source-ai-models

github.com/HiDream-ai/HiDream-O1-Image

fireworks.ai/blog/best-open-source-llms

github.com/MoonshotAI/Kimi-K2.5?tab=readme-ov-file

github.com/PolarSeeker/OpenSeeker

onyx.app/insights/best-open-source-llms-2026

fireworks.ai/blog/best-open-source-llms

onyx.app/open-llm-leaderboard

github.com/MoonshotAI/Kimi-K2.5?tab=readme-ov-file

github.com/PolarSeeker/OpenSeeker

onyx.app/insights/best-open-source-llms-2026

fireworks.ai/blog/best-open-source-llms

onyx.app/open-llm-leaderboard

github.com/MoonshotAI/Kimi-K2.5?tab=readme-ov-file

github.com/PolarSeeker/OpenSeeker

onyx.app/insights/best-open-source-llms-2026

fireworks.ai/blog/best-open-source-llms

onyx.app/open-llm-leaderboard

github.com/MoonshotAI/Kimi-K2.5?tab=readme-ov-file

github.com/PolarSeeker/OpenSeeker

onyx.app/insights/best-open-source-llms-2026

fireworks.ai/blog/best-open-source-llms

onyx.app/open-llm-leaderboard

github.com/MoonshotAI/Kimi-K2.5?tab=readme-ov-file

github.com/PolarSeeker/OpenSeeker

onyx.app/insights/best-open-source-llms-2026

The web,

organized for agents

One API for search, crawling, and research agents

Try API for free

SearchAgent

latency

Fast450msAuto1sDeep\~10s

category

Full WebNewsCompaniesResearchPeopleFinancials

API Playground

output

ResultsAnswerStructured

↓ 79% tokens

zai-org/GLM-5github.comGLM-5.1 is our next-generation flagship model for agentic engineering, with significantly stronger coding capabilities than its predecessor. It achieves state-of-the-art performance on SWE-Bench Pro and leads GLM-5 by a wide margin on NL2Repo (repo generation) and Terminal-Bench 2.0 (real-world terminal tasks).MoonshotAI/Kimi-K2.5github.com15 trillion mixed visual and text tokens atop Kimi-K2-Base. It seamlessly integrates vision and language understanding with advanced agentic capabilities, instant and thinking modes, as well as conversational and agentic paradigms. ### Key Features - \\*Native Multimodality\\: Pre-trained on vision–language tokens,Kimi K2.6 | OpenLM.aiopenlm.aiopen-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed visual and text tokens atop Kimi-K2-Base. It seamlessly integrates vision and language understanding with advanced agentic capabilities, instant and thinking modes, as well as conversational and agentic[PolarSeeker/OpenSeekergithub.comwith open-source data \[...\] - \\2026.03.17\\ 🚀 We open-sourced OpenSeeker-v1 (all data and models). Using \\11.7K\\ training examples, we fine-tuned Qwen3-30B-A3B-Thinking-2507 and achieved scores of \\48.4%\\ on BrowseComp-ZH, \\29.5%\\ on BrowseComp, \\74.0%\\ on xbench-DeepSearch, and \\59.4%\\ on WideSearch.](https://github.com/PolarSeeker/OpenSeeker)Google DeepMind Releases Gemma 4, Its ‘Most Capable’ Open-Source AI Models – SMBtechsmbtech.auGoogle DeepMind (the company’s flagship artificial intelligence research and development laboratory) has released Gemma 4, a new family of open-source AI models designed for advanced reasoning and agentic workflows, available under a commercially permissive Apache 2.0 licence.Best Open Source LLMs in 2026: Rankings and Licensing Comparison | Onyx AIonyx.appThis guide covers the top 10 open-source and open-weight LLMs from the Onyx Open LLM Leaderboard, updated as of March 12, 2026.[HiDream-ai/HiDream-O1-Imagegithub.comUnified Transformer (UiT) without external V \[...\] 48. \[...\] - 🚀 \\May 14, 2026:\\ We open-sourced \\\HiDream-O1-Image-Dev-2604\\*\ with its \prompt refiner\, tailored for text-to-image generation task.](https://github.com/HiDream-ai/HiDream-O1-Image/)[Best Open Source LLMs in 2026: We Reviewed 7 Modelsfireworks.ai| Model | Release date | Params | Context window | Best for | On Fireworks | | --- | --- | --- | --- | --- | --- | \[...\] | DeepSeek v3.2 | December 1, 2025 | 671B total (37B active) | 128K - 163K tokens | Math reasoning, enterprise agents, and coding (96.0% GSM8K, 67.8% SWE-Bench) | Try in playground |](https://fireworks.ai/blog/best-open-source-llms)[The Best Open-Source LLMs in 2026 - BentoMLbentoml.com\## DeepSeek-V4 \[...\] ## MiMo-V2.5-Pro# \[...\] ## GLM-5.1# \[...\] ## Gemma 4# \[...\] Reasoning: Kimi-K2.6, MiMo-V2.5-Pro \[...\] Coding assistants: DeepSeek-V4-Pro, Kimi-K2.6 \[...\] Agentic workflows: GLM-5.1, MiMo-V2.5-Pro \[...\] General chat: DeepSeek-V4-Pro \[...\] DeepSeek-V4-Pro \[...\] OpenClaw: Kimi-K2.](https://www.bentoml.com/blog/navigating-the-world-of-open-source-large-language-models)[Best Open Source LLM Leaderboard 2026 - Onyx AIonyx.appBest Open Source \[...\] The definitive ranking of every major open source model — compared across reasoning, coding, math, software engineering, and instruction following benchmarks. \[...\] GLM-4.7 \[...\] Best Open Source Models \[...\] ## Open Source Model Benchmark Scores \[...\] K2.5 \[...\] ## Compare Open](https://onyx.app/open-llm-leaderboard)

API Playground

RequestResponse

Cursor logo

AWS logo

Databricks logo

Groq logo

Gamma logo

Monday.com logo

HubSpot logo

Lovable logo

Legora logo

Anara logo

Browserbase logo

Klarna logo

Cursor logo

AWS logo

Databricks logo

Groq logo

Gamma logo

Monday.com logo

HubSpot logo

Lovable logo

Legora logo

Anara logo

Browserbase logo

Klarna logo

Cursor logo

AWS logo

Databricks logo

Groq logo

Gamma logo

Monday.com logo

HubSpot logo

Lovable logo

Legora logo

Anara logo

Browserbase logo

Search API

Designed to make your Agent smarter

Web index

FINANCIAL DATA

COMPAW5

Cursor

Powers their coding agents with smart token-efficient search across docs and repos

All the reports

your finance agent is looking for

Comprehensive coverage over all search verticals so your agent has the right context to solve its problem

Use our search API →

Cursor

Powers their coding agents with smart token-efficient search across docs and repos

Token efficiency

Highlights: Off

90% TOKEN REDUCTION

#### Wikipedia - Boeing

airplanes , rotorcraft , rockets , satellites , and missiles worldwide. The company also provides leasing and product support services. Boeing is among the largest global aerospace manufacturers ; it is the fourth-largest defense contractor in the world based on 2022 revenue and is the largest exporter in the United States by dollar value. Boeing was founded in 1916 by William E. Boeing in Seattle , Washington.

OpenRouter

Up to 25T tokens passed to models each week are concise excerpts powered by highlights

Token-efficient contents with highlights

Specialized model trained to extract the most relevant excerpts from the web

Try it out in our API Playground →

OpenRouter

Up to 25T tokens passed to models each week are concise excerpts powered by highlights

Structured outputs

"content": {

"companies": [

{

"company_name": "General Electric",

"ceo_name": "Larry Culp",

"founded_year": 1892

},

{

"company_name": "RTX",

"ceo_name": "Christopher T. Calio",

"founded_year": 2020

},

{

"company_name": "Boeing",

"ceo_name": "Kelly Ortberg",

"founded_year": 1916

}

]

}

HubSpot

Extracts enrichments as structured outputs across 70M+ companies with Exa

Low-latency to deep research

in one API

Configure for fast results or deep research with structured outputs and grounded citations

Integrate Exa with your agent →

HubSpot

Extracts enrichments as structured outputs across 70M+ companies with Exa

Benchmarks

Highest quality search at every latency

Best-in-class accuracy for every search vertical and across the most challenging benchmarks

AccuracyLatencySearch Verticals

Exa Instant returns results in under 180ms, faster than any other search provider.

Accuracy

Exa leads across FRAMES, Tip-of-Tongue, and Seal0 — the most demanding retrieval benchmarks.

Latency

Exa Instant returns results in under 180ms, faster than any other search provider.

Search Verticals

Best-in-class across company search, people search, and code — not just general web queries.

Exa

TavilyTavily

Brave

Parallel

Exa

TavilyTavily

Brave

Parallel

Parallel

Brave

Tavily Ultra Fast

Exa Instant

3051ms

559ms

Tavily

260ms

178ms

050010001500200025003000

Exa

TavilyTavily

Brave

Parallel

Parallel

Brave

Tavily Ultra Fast

Exa Instant

3051ms

559ms

Tavily

260ms

178ms

050010001500200025003000

Trusted by world-class teams

View all customer stories

Cognition

Exa powers all parts of Devin. We found that traditional search engine solutions were not enough. We chose Exa because it actually lets Devin search in a way that is natural for agents and returns content in a format that it can actually digest.

Walden Yan

Walden Yan

Co-founder, Cognition

HubSpot

Exa is necessary for agents on HubSpot to supplement internal data with high quality, real-time people and company search. We found that other alternatives were slower, more expensive, and did not have comprehensive enrichment coverage.

Praty Sharma

Praty Sharma

AI Lead, HubSpot

monday.com

We're entering a new era where software actually does the work. For that to be real, the agents need live intelligence behind them. Exa is where that comes from: current company and people data sourced from the web in real time.

Daniel Lereya

Daniel Lereya

Chief Product and Technology Officer, monday.com

CodeRabbit

Exa consistently shows higher quality than other AI search providers we tested. What Exa is able to do in 1 search took our old provider multiple searches, taking 5 times as long.

David Loker

David Loker

VP of AI, CodeRabbit

11x

Standard signals like funding, job changes, and hiring are commoditized. Exa is how we find leads surfacing the triggers that actually predict a good prospect, then go deep on research before our agent engages.

Prabhav Jain

Prabhav Jain

CEO at 11x

OpenRouter

OpenRouter has a laser focus on bringing a great developer experience to all language models, and Exa is the best way we've found for grounding AI in the real world in a model-agnostic way.

Alex Atallah

Alex Atallah

CEO, OpenRouter

Anara

Exa's strong coverage and flexible API have been a key differentiator for us. Scientists trust our product further when the relevant papers they expect to see are available to them in the right workflows. The ability to customize search based on the use case easily, is important.

Naveed Janmohamed

Naveed Janmohamed

CEO, Anara

Obvious

When we saw companies show up in Exa that we hadn't found anywhere else, we knew it was our best option. It delivers, for a few dollars, what we'd been spending hundreds of thousands to assemble.

David Boskovic

David Boskovic

CEO, Obvious

WebFX

We use Exa for essentially all parts of our research—gathering sources, documenting, creating notes, and building briefs.

Christopher Varner

Christopher Varner

Head of Results Innovation

StackAI

StackAI and Exa are the dream team…Exa is amazing at web search! We're proud to use Exa on our platform and to show our customers how web search can power AI agent workflows.

Bernard Aceituno

Bernard Aceituno

Co-founder and President, StackAI

Databricks

Models are only as good as the data they're trained on, and Exa's search allowed us to get high quality data we couldn't find any other way.

Jonathan Frankle

Jonathan Frankle

Chief AI scientist, Databricks

Enterprise-grade security

and controls

Talk to an expert→

###### Zero Data Retention

Ensure true privacy and compliance with customized ZDR. All queries and data can be automatically purged based on your requirements.

###### SOC 2 Type II Certified

Our security framework maintains the highest level of compliance with industry standards. Safe information processing and access control.

###### Single-Sign On

A seamless, secure login experience for your entire team. Built-in team authentication and authorization management.

pura: loading…

☰

📷 🔍 Discover ●◼ –

Ready

exa.ai · 76 images · 53 links

Comments (0)

No comments yet