Exa Release Notes

Exa Agent and Exa Connect in MCP

Exa Agent is now available within Exa MCP. Use it from Claude, Cursor, or any other MCP client when the task needs more than a single search call.

Enable the Agent tools with https://mcp.exa.ai/mcp?tools=agent_tools

Create a run with agent_create_run

Poll it with agent_wait_for_run

Read the output with agent_get_run_output

Exa Connect data sources are available through the Agent flow, so you can attach premium data partners when a run needs more than web search alone.

Read the Exa MCP guide → · Read the Exa Agent guide → · Announcement tweet →

We're releasing Exa Agent: a single API to access frontier web research capabilities at a fraction of the cost.

Exa Agent combines top language models with Exa's state-of-the-art web search tools to achieve the most exhaustive and accurate results now used in a variety of agentic products.

Exa Agent capabilities

Exa Agent is highly effective on deep research, list-building, and entity enrichment tasks.

When working with large datasets, Exa Agent divides the task into many subtasks and assigns subagents to research various domains at once. When researching, it uses a fusion of frontier and cost-effective models to find the most cost-effective methodology for the given research task.

To quantify performance, we used an array of public benchmarks that measure quality, latency, cost and token efficiency.

Our goal was to produce the best web research agent using methodologies like model fusion and Exa's token-efficient highlights model (which have shown up to 94% reductions in token usage). The result is significantly lower cost and latency for frontier performance.

Benchmark chart examples

WideSearch

BrowseComp

DeepSearchQA

FinanceAgent-V2

People-FindAll

Company-FindAll

WideSearch Methodology

WideSearch was introduced in August 2025 to evaluate agents' abilities to aggregate and structure atomic information about entities from across the web. The expected output is always a table, structured as a list of enriched entities.

The English version contains 100 tasks, with the number of required columns varying from 3 to 14. In our setup, we evaluate only the agent's final answer. We compute F1 over rows: a row is counted as successful only if the matched entity and all required enrichment columns are valid. Otherwise, it is counted as a miss.

We experimented with cell-level F1, but found it too permissive because it rewards isolated enrichment values even when the agent failed to ground them to the correct entity.

How teams are using Exa Agent

Companies building their own agents can plug into the Exa Agent API directly.

Finance Agents can take advantage of Exa Agent's ability to retrieve real-time data from across the web, aggregating it into any output format required.

Go-to-market agents can bring their own list of accounts or prospects to enrich, or use Exa Agent's list-building capabilities to generate lists of tens or hundreds of entities.

Agent output examples

Company Research

Data Enrichment

Code Review

Literature Review

Research all publicly available information on Databricks: recent funding, product launches, partnerships, executive hires, conference talks, and public GitHub activity.

Exa Agent API result

Run completed June 16, 2026

Compiled a compact Databricks company brief across funding, launches, partnerships, hires, events, and public GitHub activity. The main signal is momentum from a $134B February financing and a product narrative around governed enterprise AI agents, Lakebase, Genie, and OpenSharing.

Area Finding Evidence

1 Recent funding $7B announced in February 2026 at a $134B valuation

Databricks announced more than $7B total investment, including about $5B equity and about $2B additional debt capacity. Reports also cited discussions for a possible $165B-$175B round in June.

2 Product launches OpenSharing, Agent Bricks, Lakebase, Genie, AI Gateway, and Lakeflow

Recent launches cluster around governed enterprise agents, model access, serverless Postgres for AI agents, conversational analytics, open data/AI asset sharing, and data engineering.

3 Partnerships Frontier model, SI, open-source, and data ecosystem partnerships

The partner map includes Anthropic, Accenture, OpenAI, Linux Foundation OpenSharing, and ecosystem partners such as SAP, Stripe, Atlassian, Retool, LlamaIndex, Collibra, Deloitte, and Wipro.

• 4 more rows

Notes

Compiled from Databricks press releases, blogs, docs, GitHub pages, Reuters/MarketScreener reporting, Linux Foundation materials, and conference pages as of 2026-06-16. The June 2026 valuation item is reported discussion, not confirmed closed financing.

Try the API today

Exa Agent using auto effort will dynamically scale to the amount of compute required by the given task. Developers can also set an effort level for fixed costs:

Effort Cost Best for

minimal $0.012 / request Lightweight tasks, lowest cost

low $0.025 / request Simple lookups, narrow factual tasks, short answers

medium $0.10 / request Default starting point for most standard research tasks

high $0.50 / request Harder research, more citations, stricter completeness

xhigh $1.00 / request High-value tasks where completeness matters more than cost/latency

The API also allows developers to use structured outputs via the outputSchema parameter, and to bring their own data using input.data. Exa Agent uses many tools to operate efficiently over large datasets.

Exa Agent is available today. Read the docs or try it in the Exa API Playground: dashboard.exa.ai/playground/agent

Cheers,
The Exa Team

Introducing Exa Agent

We released a new class of frontier web research agents that are accessible via API.

Exa Agent API supports parameters including a natural-language query, effort mode, outputSchema for structured outputs, and input.data to build upon an existing dataset.

Read the Exa Agent API guide →

Introducing Exa Connect

Exa Connect gives Exa Agent live access to the world's public and private data. It launched with Similarweb, Fiber.ai, Baselayer, Financial Datasets, Affiliate.com, Particle, Jinko, and Additional Partners. You attach them via dataSources on POST /agent/runs.

Read the Exa Connect guide → · Announcement tweet →

Introducing Exa Monitors

Monitors run Exa searches on a schedule and deliver results to your webhook, deduplicated against previous runs so you only get new content.

Track topics over time: competitor news, funding rounds, regulatory changes, research papers.

Structured results: return plain text or typed JSON via outputSchema.

Flexible scheduling: run on an interval (minimum 1 hour) or trigger manually.

Read the Monitors API guide →

Exa Deep Revamp

Exa Deep is faster, cheaper, and now supports structured outputs with field-level grounding.

New deep-reasoning type for higher-effort tasks (12-50s); deep runs in 4-12s.

20% lower price for regular deep search.

Structured outputs via outputSchema, with output.content and output.grounding (field-level citations and confidence) in the response.

See the Exa Pricing Update below for full pricing.

Read the Search API reference →

Exa Pricing Update

We simplified and lowered pricing. Contents for the first 10 search results are now included for free, and the new pricing applies automatically with no action needed.

Search with contents: $7 per 1k requests (10 results, text + highlights included); $1 per 1k additional results.

Summaries: $1 per 1k, on both search and contents.

Exa Deep: $12 per 1k requests; Deep (Reasoning) $15 per 1k.

Contents endpoint: $1 per 1k pages per content type.

View current pricing →

Introducing Exa Instant Search

Exa Instant is our fastest search type, combining improved neural search quality with sub-150ms latency. Enable it with type="instant".

Built for real-time: chat apps, voice AI, coding agents, autocomplete, and live suggestions.

State-of-the-art quality at the lowest latency we offer.

Read the Search API guide → · Try it in the dashboard →

Highlights, content freshness, and MCP updates

Three improvements to content extraction and access:

• maxCharacters for highlights: now the preferred way to control highlight length. numSentences and highlightsPerUrl are deprecated.
• maxAgeHours for content freshness: age-based control replacing boolean livecrawl (0 always crawls, -1 cache-only, 24 crawls if older than 24h).
• Exa MCP free tier: try it unauthenticated at 3 QPS and 150 calls/day; add an API key for full access.

Content freshness docs → · Exa MCP →

JS SDK: highlights restored

Highlights are back in the JavaScript SDK as of exa-js v2.0.11, returning key sentences with relevance scores. Pass highlights: true or highlights: { maxCharacters, query } in search and contents calls.
Read the JavaScript SDK docs →

New Deep Search Type

Exa Deep finds better results by running multiple searches at once and returning high-quality context for each result. Enable it with type="deep".

Query expansion: send one query and we generate variations, or supply your own with additionalQueries.

Parallel search and smart ranking across your query and all variations.

Detailed summaries for each result.

Read the Search API reference →

Added Language Filtering

Exa now detects your query language and returns results only in that language. Enabled by default for all users, with no setup required.

Read the Search API guide →

Geolocation Filter Support

The new userLocation parameter biases results toward a user's region, passed as an ISO 3166-1 alpha-2 country code (e.g. "us", "fr"). Useful for multi-regional apps, regional-language content, and local discovery.

Read the Search API reference →

New Fast Search Type

Exa Fast uses streamlined search models with p50 latency below 425ms. Enable it with type="fast".

• Same Exa index of high-quality content as neural search.
• Full parameter compatibility with other search types.
• Built for fast web grounding, agentic workflows, and low-latency products.

Read the Search API guide → · Try it in the dashboard →

Score Deprecation in Auto Search

A new Auto search architecture can no longer produce meaningful relevance scores, so the score field is being removed from Auto search results.

• Auto search: no longer returns score; results are already ranked by relevance.
• Neural search: scores are unchanged. Set type="neural" if you depend on them.

Read the Search API reference →

Markdown Contents as Default

All endpoints now return clean markdown by default, which is better for LLMs, RAG, and general text processing. No action needed.

includeHtmlTags=false (default): content processed into clean markdown.

includeHtmlTags=true: raw HTML without markdown processing.

Either way, boilerplate like ads and navigation is stripped.

Read the Contents docs →

New Livecrawl Option: Preferred

livecrawl: "preferred" attempts a fresh crawl but falls back to cached content when crawling fails (unlike "always", which errors). Ideal for production apps that want fresh content without failing on temporarily unavailable sites.

Read the Content Freshness docs →