Best API for company news
Two kinds of product answer this question: general web search APIs that search the open web, and dedicated news indexes built specifically for press releases, wires and company newsrooms. Both are measured here on the identical question set, with the same query, the same result cap and the same judge.
The purpose-built index does not win. Exa (type=deep), a general web search API, answers 99.2% of the questions correctly. The strongest dedicated news index, PredictLeads, reaches 69.0% — a gap of 30.2 points on the job it was built for.
Web search APIs for company news · News index APIs · Web search API benchmark
Every endpoint, on the same company-news questions
Banded by mechanism and ranked inside each band. A rank across the two would claim they are substitutes; keeping them on one board is what makes the comparison visible.
| Rank | Vendor | Endpoint & configuration | Accuracy | AR@1 | AR@5 | Latency | Snippet tokens | Total $ | Official docs |
|---|---|---|---|---|---|---|---|---|---|
| Web search | |||||||||
| 1 | Exaweb search | POST /searchtype=deep | 99.2% | 98.5% | 100.0% | 3.00s | 1,330 | $1.65 | Official docs |
| 2 | Exaweb search | POST /searchtype=instant | 97.7% | 83.7% | 97.7% | 447ms | 2,051 | $1.05 | Official docs |
| 3 | Parallelweb search | POST /v1/searchmode=advanced | 96.9% | 62.0% | 96.9% | 3.28s | 2,127 | $0.80 | Official docs |
| 4 | Linkupweb search | POST /v1/searchdepth=standard · outputType=searchResults | 96.1% | 80.6% | 93.0% | 2.34s | 2,926 | $0.83 | Official docs |
| 5 | Parallelweb search | POST /v1/searchmode=basic | 95.3% | 65.1% | 91.5% | 1.41s | 2,409 | $0.82 | Official docs |
| 6 | Linkupweb search | POST /v1/searchdepth=fast · outputType=searchResults | 94.6% | 88.4% | 95.3% | 1.82s | 2,838 | $0.82 | Official docs |
| 7 | Tavilyweb search | POST /searchsearch_depth=advanced · chunks_per_source=3 | 93.8% | 79.8% | 94.6% | 4.40s | 3,041 | $2.25 | Official docs |
| 8 | Brave Searchweb search | GET /res/v1/web/searchcount=10 · result_filter=web | 93.8% | 83.7% | 93.8% | 693ms | 723 | $0.73 | Official docs |
| 9 | SERPgoogle search | GET google-search74.p.rapidapi.comlimit=10 | 93.0% | 73.6% | 93.0% | 2.04s | 469 | $0.46 | Official docs |
| 10 | Firecrawlweb search | POST /v2/search | 92.3% | 74.4% | 92.3% | 1.42s | 672 | $0.73 | Official docs |
| News index | |||||||||
| 1 | PredictLeadscompany news events | GET /api/v3/companies/{domain}/news_eventscategories[] · paginated | 69.0% | 62.0% | 72.1% | 651ms | 302 | $5.23 | Official docs |
| 2 | Seltznews index | POST /v1/searchscope=news | 66.7% | 31.8% | 63.6% | 330ms | 2,915 | $0.82 | Official docs |
Company news APIs
What is the best API for company news?
On 129 company-news lookups, Exa (type=deep) answers 99.2% correctly — a general web search API, not a news product. The strongest dedicated news index, PredictLeads, reaches 69.0% on the identical set.
Do dedicated news APIs beat web search for company news?
Not on this run. The best general search endpoint is 30.2 points ahead of the best dedicated news index on the same questions, with the same query, the same result cap and the same judge.
What counts as a company-news lookup here?
A factual question about a recent company event — a layoff, product launch, acquisition, funding round, leadership change or expansion — with a single verifiable answer pinned to an official wire or newsroom URL. Factual questions are used because they have a ground truth that does not depend on taste.
Why are the two kinds of API ranked separately?
Because they are different mechanisms and a single ranking would imply they are substitutes. They are kept on one board, banded and ranked within each band, so the comparison stays visible without the ranking making a claim it cannot support.
How is this measured?
Every endpoint receives the identical user query and may return at most 10 results. The returned snippets are read by one extraction model and judged by claude-opus-5 via Amazon Bedrock against ground truth reviewed from official sources. Nothing is rewritten per vendor.