Vercel AI Gateway adds Browserbase Search and Fetch tools for web access
Vercel has added Browserbase Search and Fetch to AI Gateway, letting developers give their models access to current web information and page contents. According to Vercel, the tools work with any model that supports tool calling and need only one API key.
- Browserbase Search and Fetch are now available through Vercel's AI Gateway.
- The tools work with any model that supports tool calling and use one API key.
- The helpers require AI SDK 7.0.116 or later.
- Developers pass browserbase_search and browserbase_fetch in the tools option.
- Pricing and configuration options are listed in the Browserbase documentation.
What the new tools do
Browserbase Search and Fetch are now available through AI Gateway, Vercel's service for calling models through a single API. The two tools let a model find relevant pages on the web and then retrieve their contents. Vercel says this gives models access to current information.
The tools arrive alongside Browserbase's existing integrations with the AI SDK and the Vercel Marketplace. Through AI Gateway, Browserbase's tools can be used across model providers with one API key, according to Vercel. Developers can add web search and page retrieval to any model that supports tool calling, and keep the same tools when they switch models.
How to set it up
The helpers are available in AI SDK 7.0.116 and later. Vercel instructs developers to update with pnpm add ai@latest and to set their AI_GATEWAY_API_KEY.
To enable the tools, developers pass the helpers in the tools option. In Vercel's example, a streamText call uses the model moonshotai/kimi-k3 and a prompt asking it to find Browserbase's latest announcement, fetch the page and summarize it. The tools are registered as browserbase_search, using gateway.tools.browserbaseSearch with numResults set to 3, and browserbase_fetch, using gateway.tools.browserbaseFetch with allowRedirects set to true.
Vercel points to the Browserbase Search and Fetch documentation for pricing and configuration options. The tools can also be tried in the AI Gateway model playground, and the model catalog is available for exploring supported models.
What it means for developers
For teams building on AI Gateway, the change means web search and page retrieval no longer have to be wired up separately for each model provider. Because the same tools carry over when the underlying model changes, developers can swap models without reworking how their application reaches the web.
AI Gateway itself provides one API for calling models, tracking usage and cost, and configuring routing, retries and failover. Users can authenticate with an AI Gateway API key or bring their own provider key. The Browserbase tools extend that setup with web access, while pricing details remain in the Browserbase documentation.
Vercel: AI Gateway adds Browserbase Search and Fetch tools
