Parallel Search is now available in @baseten.
Pick Parallel for the most accurate web search at the lowest price. Your agents will thank you for the upgrade.
Your web search shouldn’t cost more than your inference.
It's simple:
If you’re using GPT 5.6 Luna or similarly priced models, chances are you’re overpaying for search.
Today, @ArtificialAnlys announced their new Search Index, ranking leading web search APIs across quality, speed, and cost.
On an equal-weighted mean of DeepSearchQA F1, BrowseComp accuracy, and AA-Omniscience accuracy, Parallel is ranked #1#.
lets agents call Parallel's Search, Extract, and Task APIs with no API key and no human authentication, paying per request with stablecoins on @tempo or x402 on Base.
Today's tech blog from @0xsunny77 walks through how we built the gateway: