Request wave insights
Answers 202: generation is scheduled, not done. Poll the GET above rather than re-requesting.
SPENDS. This runs models on your organization’s account and draws on the insightsPerDay ledger, which is SHARED with eval-run and user-testing insights — burning it here takes it from there too.
Three refusals, and they mean different things:
429withcode: "RATE_LIMITED"and a shortRetry-After— the per-minute burst brake. Wait seconds.429naminginsightsPerDayindetails— the daily ledger.Retry-Aftercounts to UTC midnight.403— the feature is not available to your organization. Waiting will never help; collapsing this into the 429s would send someone who hit today’s cap shopping for a plan they already have.
Authorizations
MCPJam API key (sk_…). Create one at Settings → API keys. Guest sessions cannot use the API, and API keys cannot manage other API keys.
Path Parameters
ID of the hosted project that contains the server.
Wave ID — the opaque group id shared by every run of one co-launched swarm. Returned on every run in the wave.
Body
Optional. Omit the body entirely for the common case.
Regenerate over a wave that already has insights. OFF by default because it SPENDS a second time against your organization's shared daily ledger — and the common cause of a repeated request is a caller that did not poll.

