Expand Search is here.

Two weeks ago, we launched Expand Fetch, a page-reading API powered by models we trained from scratch. It preserves tables, icons and hidden data.

It's already handling millions of requests in production. But our users keep telling us they're frustrated with the search APIs they use alongside Fetch.

If your agent gets one search to answer a question, finding the right source is critical. When it's doing deep research, every query adds up.

Today we're introducing Expand Search, a web search API for agents on the price–accuracy Pareto frontier of the APIs we tested, at $1.50 per 1,000 searches. No search API we tested matches Expand's accuracy at a lower price.

Watch the launch0:29

Search is available today through our API, TypeScript SDK, CLI and MCP server.

An animated example of Expand Search. The question "how do I rotate a Stripe API key" is entered automatically. Search returns three ranked pages from Stripe documentation, HowToRotate and Stripe Support, each with a title, excerpt and relevance score. Results are from a saved search.

how do I rotate a Stripe API key

docs.stripe.com/keys0.994

API keys | Stripe Documentation

On the API keys page, click the overflow menu for the key you want to rotate. Select Rotate key. Select an expiration date from the Expiration dropdown.

howtorotate.com/docs/tutorials/stripe0.994

Stripe - How to Rotate Leaked API Keys

This tutorial provides step-by-step instructions on how to rotate a Stripe API key. Generate a new Stripe API key. Navigate to the API key page.

support.stripe.com0.991

How do I rotate/change/update my Stripe API key?

Rotating a key revokes it and generates a replacement key. You can rotate a key immediately or schedule a key to rotate after a certain time.

Ranked for your question

How it compares

We compared Expand with seven other search providers on five public benchmarks covering coding questions, factual lookups and multi-step research. Our composite index averages answer accuracy across these public benchmarks, giving each equal weight.

Expand scored highest and was Pareto-optimal on our index. It delivered accuracy comparable to Exa Auto and Brave LLM Context at less than a third of the cost. No other configuration we tested matched its score for less money.

Similar overall scores can hide very different tradeoffs. Some APIs reach comparable accuracy at several times the search spend. Others cost less per query but fall behind when the agent has only one search to work with. The comparisons below show where Expand's price buys you more.

Expand vs Exa and Brave

The price per 1,000 searches doesn't tell you what a research task will cost. Agents can search repeatedly as they investigate a question. Those calls add up.

On the 600-question AA-Omniscience benchmark, Expand reached 90.7% accuracy, with search spend of $4.62 per 1,000 questions and an average of 3.1 searches per question. Exa's and Brave's search APIs scored between 88.3% and 89.8%, with search costs ranging from $13.56 to $23.75 and averages of 3.2–3.9 searches per question.

Expand vs Perplexity and Parallel

Sometimes your agent has to answer after a single search. There's no follow-up query to fill in what it missed. In that setting, accuracy matters more than saving a fraction of a cent on the call.

Expand costs $0.0015 per search, compared with $0.001 for Perplexity Fast. Expand reached 52.8% accuracy on SEAL-Hard's 254 questions, versus Perplexity's 45.3%. On the 824-question FRAMES benchmark, it scored 75.8% versus 72.8%. Across both benchmarks, the model answered 44 more questions correctly using Expand, a 6% increase for $0.54 in additional search spend. On WebCode, SimpleQA Verified and AA-Omniscience the two were level.

Parallel Fast and Turbo cost just $0.0005 less per search than Expand. On our composite index, Expand scored significantly higher than both: 80.9, compared with 76.5 for Fast and 76.3 for Turbo. It also had significant leads over Turbo on SEAL-Hard's 254 questions, scoring 52.8% versus 41.3%, and over Fast on AA-Omniscience's 600 questions, at 90.7% versus 87.7%.

Expand vs Firecrawl

You don't need a bigger search budget to get more answers right. For less than Firecrawl's search price, Expand outperformed Firecrawl on every benchmark we tested, by as much as 36 percentage points.

The biggest gap was on WebCode, where Expand reached 87.6% accuracy versus Firecrawl's 51.8%. Similarly, it scored 52.8% versus 41.3% on SEAL-Hard, and an F1 score of 97.6% versus 91.4% on SimpleQA Verified.

Firecrawl returns titles, URLs and short descriptions, averaging only 112 tokens of evidence per result in our runs, compared with Expand's 523. Expand returns richer, query-relevant excerpts your agent can use to answer directly. If your agent needs more context than Firecrawl's snippet provides, it has to fetch the page, using additional credits.

If you're using Firecrawl for search or page reading, switch to Expand Search and Fetch.

How we tested

We tested Expand Search against other providers in two settings: single-shot, where the model gets one search call before answering, and research agent, where it can search and fetch pages for up to 25 turns before submitting its answer.

Within each benchmark, all providers were evaluated on the same questions, using the same models and prompts to generate and grade the answers.

Benchmarks

Our benchmark writeups explain each protocol, the graders and how our setup differs from the original evaluations.

Scoring

For each provider, we calculate the percentage of questions answered correctly on each benchmark, then average those five percentages to produce the composite index. Each benchmark gets equal weight, regardless of how many questions it contains.

The WebCode tab displays evidence coverage, and the SimpleQA tab displays F1. These are separate metrics. The composite index uses answer accuracy for both.

Costs

The overall chart shows the price per 1,000 searches. Individual benchmark tabs show search spend per 1,000 questions, including every search the agent makes on AA-Omniscience. Model and grading costs are excluded. Prices are for the specific configurations we tested.

Evaluation details

Each configuration attempted the full question set for every benchmark, with one run between October 26 and 28, 2026. Questions left unanswered because of API errors after retries received no credit and remained in the total question count. We calculated 95% confidence intervals by repeatedly resampling the recorded per-question results. These intervals reflect variation across questions. They do not measure how results might change across repeated runs or different grading models.

These results come from our evaluation setup and are not directly comparable with the benchmarks' original leaderboards. Expand had the highest composite score. Its lead over Exa Auto, Exa Lite, Exa Fast and Brave LLM Context is within the margin of error. It is significantly ahead of the other seven configurations.

Evaluation code, prompts and per-question results are available in the benchmark repository.

Search is our second product launch, following Expand Fetch. We're building toward a web your agents can query like a database. Join the waitlist for what's next.

About Expand

Expand is an applied research lab building web data APIs for AI agents. We design and train our own models from scratch.