Web search, Extract (page to markdown) and Render for AI agents. Pay per call in USDC via native x402 on Base. No account, no API key. Also on Pocket Network.
Thanks for publishing the real numbers, especially that all 4 payments came from verifiers. That's the honest part most x402 write-ups skip. Claude Code and Codex stopping at the payment error makes sense, since most MCP clients have no wallet at all, so 3 free calls a day marked in meta.free_call feels like the right fix. Did those free calls change how many developers came back on a second day? That would tell you whether it's a discovery problem or a payment problem.
Thanks! Honestly too early to tell: free calls went live yesterday and no outside client has used one yet. The quota key rotates daily for privacy, so I’m adding a stable anonymous id to measure day-2 returns. Will share the numbers in a follow-up.
Web search, Extract (page to markdown) and Render for AI agents. Pay per call in USDC via native x402 on Base. No account, no API key. Also on Pocket Network.
Makes sense. A stable anon id should give a much cleaner day-2 number. Might also be worth tagging calls by client (user-agent or MCP client name) so your own tests and health checks don't get counted as returning users. Looking forward to the follow-up.
Good call, done. initialize now logs the MCP client’s name/version, so returns can be split by client (Claude Code, Cursor, …). Self-identified bots and health checks were already excluded from the funnel, and our own tests now send a bot user agent so they’re excluded too. Follow-up coming once there’s a week of data.
Web search, Extract (page to markdown) and Render for AI agents. Pay per call in USDC via native x402 on Base. No account, no API key. Also on Pocket Network.
The distinction between a verifier paying and someone wanting the result is the useful part of this report. For the free-preview experiment, I would track a smaller funnel: discovery, valid task-specific call, useful preview delivered, then a return for a different task after the free allowance. Count logical attempts separately from HTTP retries, and keep operator tests and known verifiers separate from unclassified traffic. Unclassified should not automatically mean a real buyer; IPs and user-agent strings are weak identity evidence.
One no-payment fixture could help isolate the client issue: run the same valid query in a client without payment support, return the preview plus an explicit payment-required state, and check whether it can explain the next step without retrying the paid tool or treating the preview as the full result. That separates demand for the answer from ability to complete the payment flow.
Are you measuring return use of the previews separately from paid conversion? That might reveal a useful workflow before wallet interoperability catches up.
Thanks, this is a sharper funnel than what I’m tracking. Today I separate self-identified bots, our own tests and known verifiers, but “unclassified” is still a bucket, not a buyer. The free calls are only a day old and haven’t had an external user yet, so there’s no return data. I’ll add a stable anonymous client id so I can see whether anyone comes back for a different task after the allowance, separately from paid conversion.
That separation makes sense. One small acceptance fixture for the anonymous ID: the same client retries task A, then completes a genuinely different task B; another client submits the identical task A. The first retry should not count as return use, while the second client should not be merged with the first just because the query matches.
I would keep the client ID independent of IP/user-agent and of the task key, and treat it as a continuity hint rather than proof of a unique person. A reset or reinstall should remain an unknown/new-client case, not a recovered identity. No payment is needed for this test. That would give the return-use number a clear meaning before there is enough traffic to interpret conversion.
Good test. Most of it holds today: return use only counts activity on a different UTC day, so same-day retries don’t count, and the id ignores the query and the user agent. It’s a keyed hash of the address (IPv6 by /64), so it’s a continuity hint, not a person. Shared egress can merge unrelated clients, and a new network looks like a new client. One nice side effect of ignoring the user agent: it showed that one developer had us in both Codex and Claude Code.
Thanks, that makes the metric much easier to interpret. I'd put two cases next to the same-day retry test: two unrelated clients use the same shared egress on successive UTC days (one apparent return), then the same client uses different egress on successive days (no observed return). Both can pass the current implementation while showing why the number describes returning network identifiers rather than returning clients.
I'd label it that way in the dashboard and show the numerator and denominator alongside the rate. No need to add browser fingerprinting to make the label more precise.
Agreed, and the data already shows your second case: the one developer I can identify reappeared under three ids last week after switching networks, with identical client versions. I’ll relabel it as returning network ids and show the counts next to the rate. No fingerprinting planned.
Thirty-day production notes are more useful than launch metrics because they reveal where the contract actually bends. I would separate demand, successful paid calls, refunded or failed calls, support load, and provider costs by endpoint. That makes pricing decisions traceable to real usage rather than aggregate revenue.
Agreed, and most of that split exists already: per-endpoint 402s (demand), paid calls, and failures, which are never charged since settlement only happens on a 2xx. Support load is zero so far. The real “provider cost” on the free tier isn’t money but D1’s daily read and write limits, which I’ve hit once. The honest 30-day number is that all paid calls so far came from verifiers and directory checks, so there’s no pricing signal yet. That will be the core of the follow-up post.
We're a place where coders share, stay up-to-date and grow their careers.
Thanks for publishing the real numbers, especially that all 4 payments came from verifiers. That's the honest part most x402 write-ups skip. Claude Code and Codex stopping at the payment error makes sense, since most MCP clients have no wallet at all, so 3 free calls a day marked in meta.free_call feels like the right fix. Did those free calls change how many developers came back on a second day? That would tell you whether it's a discovery problem or a payment problem.
Thanks! Honestly too early to tell: free calls went live yesterday and no outside client has used one yet. The quota key rotates daily for privacy, so I’m adding a stable anonymous id to measure day-2 returns. Will share the numbers in a follow-up.
Makes sense. A stable anon id should give a much cleaner day-2 number. Might also be worth tagging calls by client (user-agent or MCP client name) so your own tests and health checks don't get counted as returning users. Looking forward to the follow-up.
Good call, done. initialize now logs the MCP client’s name/version, so returns can be split by client (Claude Code, Cursor, …). Self-identified bots and health checks were already excluded from the funnel, and our own tests now send a bot user agent so they’re excluded too. Follow-up coming once there’s a week of data.
Nice, splitting by client name from initialize is cleaner than guessing from user agents. Looking forward to the week-one numbers.
The distinction between a verifier paying and someone wanting the result is the useful part of this report. For the free-preview experiment, I would track a smaller funnel: discovery, valid task-specific call, useful preview delivered, then a return for a different task after the free allowance. Count logical attempts separately from HTTP retries, and keep operator tests and known verifiers separate from unclassified traffic. Unclassified should not automatically mean a real buyer; IPs and user-agent strings are weak identity evidence.
One no-payment fixture could help isolate the client issue: run the same valid query in a client without payment support, return the preview plus an explicit payment-required state, and check whether it can explain the next step without retrying the paid tool or treating the preview as the full result. That separates demand for the answer from ability to complete the payment flow.
Are you measuring return use of the previews separately from paid conversion? That might reveal a useful workflow before wallet interoperability catches up.
Thanks, this is a sharper funnel than what I’m tracking. Today I separate self-identified bots, our own tests and known verifiers, but “unclassified” is still a bucket, not a buyer. The free calls are only a day old and haven’t had an external user yet, so there’s no return data. I’ll add a stable anonymous client id so I can see whether anyone comes back for a different task after the allowance, separately from paid conversion.
That separation makes sense. One small acceptance fixture for the anonymous ID: the same client retries task A, then completes a genuinely different task B; another client submits the identical task A. The first retry should not count as return use, while the second client should not be merged with the first just because the query matches.
I would keep the client ID independent of IP/user-agent and of the task key, and treat it as a continuity hint rather than proof of a unique person. A reset or reinstall should remain an unknown/new-client case, not a recovered identity. No payment is needed for this test. That would give the return-use number a clear meaning before there is enough traffic to interpret conversion.
Good test. Most of it holds today: return use only counts activity on a different UTC day, so same-day retries don’t count, and the id ignores the query and the user agent. It’s a keyed hash of the address (IPv6 by /64), so it’s a continuity hint, not a person. Shared egress can merge unrelated clients, and a new network looks like a new client. One nice side effect of ignoring the user agent: it showed that one developer had us in both Codex and Claude Code.
Thanks, that makes the metric much easier to interpret. I'd put two cases next to the same-day retry test: two unrelated clients use the same shared egress on successive UTC days (one apparent return), then the same client uses different egress on successive days (no observed return). Both can pass the current implementation while showing why the number describes returning network identifiers rather than returning clients.
I'd label it that way in the dashboard and show the numerator and denominator alongside the rate. No need to add browser fingerprinting to make the label more precise.
Agreed, and the data already shows your second case: the one developer I can identify reappeared under three ids last week after switching networks, with identical client versions. I’ll relabel it as returning network ids and show the counts next to the rate. No fingerprinting planned.
Thirty-day production notes are more useful than launch metrics because they reveal where the contract actually bends. I would separate demand, successful paid calls, refunded or failed calls, support load, and provider costs by endpoint. That makes pricing decisions traceable to real usage rather than aggregate revenue.
Agreed, and most of that split exists already: per-endpoint 402s (demand), paid calls, and failures, which are never charged since settlement only happens on a 2xx. Support load is zero so far. The real “provider cost” on the free tier isn’t money but D1’s daily read and write limits, which I’ve hit once. The honest 30-day number is that all paid calls so far came from verifiers and directory checks, so there’s no pricing signal yet. That will be the core of the follow-up post.