Stories you can date
News results come with a publication date, so your agent never passes off an old story as today's.
News search for agents
Trawlia is a search engine for agents that is built mostly for news. Your agent answers from recent coverage it can date and cite, instead of from whatever the open web happens to rank first.
Get a free API key See what you get
$0.00613 a credit 1,000 free credits a month, no card No SDK to install
News
News is what Trawlia is mostly for, and where most of the work has gone. An agent that answers from the open web gets last year's article as readily as this morning's. Here it gets the story that is actually current.
News results come with a publication date, so your agent never passes off an old story as today's.
Ask for the last day, the last week or a set of dates, and older stories stay out of the answer.
Stories link to the outlet that wrote them, not to an aggregator, and the same article found by several sources appears once.
Need something that is not news? Trawlia searches the wider web too.
Results
Search APIs are easy to compare on price and speed; what decides whether your agent answers well is the quality of what comes back to it.
| Search API | Results returned of 20 |
|---|---|
| Trawlia | 20 |
| Engine A | 19.31 |
| Engine B | 18.13 |
| Engine C | 9.13 |
Reliability
A search that finds nothing says so, and a search that breaks says that instead. Your agent is never handed an empty answer that secretly means something went wrong.
An empty result is the web having nothing to say, never a cover for an outage, so your agent does not conclude that a story does not exist because a source was down.
When your agent reads full pages, each one that could not be retrieved comes back marked as such, with the reason, instead of vanishing from the list.
Ask for something Trawlia does not do and it refuses by name, rather than returning an answer that quietly ignores what you asked.
Ask what happened this week and get back coverage your agent can date and cite.
Search API reference →Hand over a list of links and get readable text back, ready for research or your own retrieval pipeline.
Extract page content →Add Trawlia to your assistant as a tool, with no code to write.
Connect with MCP →Speed
18ms
cached
275ms
first ask
94%
of results carried a citable publisher URL
Median of 16 fixed queries at the default search depth, measured against the live service on 2026-08-14. A call that errored is counted, never dropped.
Pricing
$0.00613a credit
On the Scale plan: $49 a month for 8,000 credits.
One balance and a published price for every operation, so you can work out what a call costs before you make it. A basic search is one credit, advanced is two, and extraction is one credit per five URLs. The free plan includes 1,000 credits each month: enough for 1,000 basic searches or 500 advanced searches. Paid plans renew monthly; see pricing for billing details.
Fit
Nothing to install and no library of ours to keep up with. Trawlia drops into an agent or a retrieval pipeline you have already built.
If your code can make a web request, it can use Trawlia. There is no SDK to learn and nothing to update when we change something.
If your agent already calls a search API of this kind, moving over is usually a change of address and key, and you can keep the rest of your code.
Point a coding agent at our setup page and it can wire Trawlia in without you reading a thing. The page comes from the code that serves your requests, so it cannot describe something that no longer exists.
Prefer to read first? Everything is in the API reference.
1,000 credits a month, no card, and the same API the paid plan gets. Run your own evaluation set through it and check the sources and content yourself.