| Limit | Value |
|---|---|
| Document state | 1 MB |
| Attributes per document | 64 |
| Documents per write | 1,000 or 64 MB |
A written document’s created_at | at most 5 minutes in the future, and not before 1970 |
| Judgments per namespace | 100 active |
| Versions per judgment | unlimited, retained forever |
| Choice options | 254 plus the injected escape option |
| Score levels | 2 to 10 |
| Compiled context | the engine’s limit (jev current: 32,000 tokens), or max_tokens if lower |
| Questions per engine request | 32 |
top_k | 1,000 |
| Namespaces per organization | unlimited |
| Namespace name | 256 bytes |
Periodic interval | at least 1 hour: each run re-judges the whole namespace |
default/quickstart | 10,000 documents and 100 MB; a write past that is refused with too_large. It is free, and its judging pauses for the month at its usage limit |
Relations
For judgments that read other documents through relations. A request over any of these is refused withinvalid_request.
| Limit | Value |
|---|---|
Keys in applies_to and in each relation’s match | 8 each |
| Relations per judgment | 4, each with a last_n, a window or both, except one that reads a referenced document, which takes neither |
last_n on a relation | 1,000 |
| Related documents a relation reads | the newest 1,000 created, whatever its last_n and window; one for a referenced document |
| Aggregate paths per relation | 8 across sum, min, max and latest |
| Bands on a field | 1 to 9 strictly increasing cut points, and one more label, each label up to 64 bytes |
| Features per composite judgment | 8 |
| Reference indexes per namespace | 3, one per attribute that relations join on, whether related documents point through it or judged documents do, counting judgments inherited from a template; an attribute used both ways is one index, and a fourth is refused and details.reference_indexes names the current ones |
| Fan-out settings | fanout.max_wait_ms at least fanout.debounce_ms; job_above and auto_daily_limit 0 or more; the namespace’s share above 0 and at most 1 |
Composite judgments
For composite judgments and their suggested parts.| Limit | Value |
|---|---|
| Parts per composite judgment | 2 to 8; 1 to 8 with features |
suggest_parts calls | 20 per judgment and 50 per organization a day, across all its namespaces; past either, rate_limited with details.limit (20 or 50, the limit reached) and details.resets_at, the next midnight UTC, and no Retry-After. A call that fails with engine_unavailable before the model ran does not count; one that timed out does |
suggest_parts count | 2 to 8 |
Labelled examples one suggest_parts call shows the LLM | at most 30, and 100,000 tokens together: each is cut to its share |
Labelled examples suggest_parts needs | 10 of each answer |
Fan-out defaults
For judgments that read the document each judged document points at: when a change to it re-judges the judged documents that point at it (the fan-out). Each is a setting you can change with aPATCH and no new version.
| Setting | Default |
|---|---|
fanout.scope.created_within | 30 days: judged documents created longer before the change keep their answer |
fanout.scope.where | none |
fanout.debounce_ms | 600,000 (10 minutes) |
fanout.max_wait_ms | 6 × fanout.debounce_ms, so 3,600,000 |
fanout.job_above | 10,000 judged documents, or the namespace’s |
fanout.confirm_jobs | true, or the namespace’s |
fanout.auto_daily_limit | 100,000 judged documents re-judged automatically in any 24 hours |
Namespace fanout.share | 0.5 of the namespace’s in-flight engine requests, always at least one |
Documents sampled for a fanout job’s estimate | 1,000 |
Requests
| Limit | Value |
|---|---|
| Estimated query scan | 4 GB; larger queries are refused with too_large and are not billed |
wait_ms on a get | 10,000 ms |
wait_timeout_ms on a write | 10,000 ms; a larger value is lowered to it |
| Documents of one write judged at interactive priority | the first 16; the rest are judged with ordinary catch-up, so a large wait_for write usually returns them pending |
| Query cursor validity | 10 minutes |
| Requests per key | 1,000 per second by default |
| Namespace size in v1 | designed for up to 100,000,000 documents or 256 GB. This is the design ceiling, not an enforced limit: a larger namespace is accepted, but its performance is not measured |