Massive

Real-time web access for your AI

[Massive @joinmassive]

@seltz_ai The full spotlight, including when to pair it with a live SERP: https://t.co/CYVhaFwl5w

[Massive @joinmassive]

Seltz (@seltz_ai) returns web search results to AI agents in about 300ms, as full-text documents from its own index.

Five endpoints, one per job: Search for raw documents, Answer for one cited answer, Fetch for URLs you have, Monitor for what's new, Agent for deep research.

[Massive @joinmassive]

@seltz_ai Pricing is per search, not per result: $3 per 1,000 on base, $5 on pro, and new accounts get $20 free. Setup in Claude Code is one claude mcp add command.

In Seltz's run of Exa's benchmark: 327ms median, 0.53 precision at 10. Exa led on top-1 accuracy.

[Massive @joinmassive]

The cases, the laws by country, and what to ask any provider (not legal advice): https://t.co/fs8g0697Qp

[Massive @joinmassive]

Are residential proxies legal? Yes. The ones in the headlines took devices without asking.

What gets networks shut down is taking devices without consent.

Sourcing, use, and local law decide

[Massive @joinmassive]

The protocols, our 42-company landscape, and the full store check: https://t.co/vCerhgOitl

[Massive @joinmassive]

Agentic commerce could handle up to $1 trillion in U.S. retail by 2030 (McKinsey).

It runs on 4 open protocols: ACP, UCP, AP2 and TAP.

We checked 36 well-known stores for the file an AI shopping agent reads first. 11 had one. Only 2 of 22 big retailers did.

[Massive @joinmassive]

The full spotlight, including what Gaffa's customers built and its plan pricing: https://t.co/RhNvKKNjNY

[Massive @joinmassive]

Gaffa runs a real cloud browser behind one REST call. Send a URL and a list of actions, get back markdown, a PDF, a screenshot, or JSON.

For residential IPs, Gaffa works with several proxy providers, and Massive is one of them.

[Massive @joinmassive]

When an agent needs geotargeting, a task-by-task table, and how to verify the location each request got: https://t.co/r9MdD1GqlK

[Massive @joinmassive]

Myth: an AI agent doesn't need a location.

It already has one. Sites read it from the IP, and the page changes with it: search results, AI answers, prices.

If you don't choose it, your server's data center does.

[Massive @joinmassive]

Every launch, its status, and the Pay Per Use mechanics: https://t.co/Yf20gboVBF

[Massive @joinmassive]

Daily AI agent requests on Cloudflare grew more than 1,700% in a year, by Cloudflare's count.

At Birthday Week two weeks ago, it added ways to charge that traffic. A thread on what is new, and what was already there:

[Massive @joinmassive]

For agent builders, "allowed or blocked" is now three lanes: identified, priced, and open.

Log which lane each source puts you in, and treat a 402 as a budget decision, not an error to retry.

[Massive @joinmassive]

The awaiting parameter in curl and Python, plus location, language, and the cache setting for fresh answers: https://t.co/YYUmVaNODv

[Massive @joinmassive]

Your rank tracker says you're #1 on Google.

The AI Overview sitting above you never made it into the data. It loads after the rest of the page.

On Massive's Search endpoint, awaiting=ai waits up to one minute for it. awaiting=answers does the same for People Also Ask.

[Massive @joinmassive]

@orthogonal_sh The full Orthogonal spotlight, including the decoded 402 response: https://t.co/r424oeFcmF

[Massive @joinmassive]

Orthogonal (@orthogonal_sh) gives AI agents one key and one balance for 1,000+ API endpoints from 60+ providers.

Massive's Search endpoint is on its x402 gateway, so we called it. Swipe for how an agent pays per request, no account needed.