> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.emtelligent.com/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.emtelligent.com/_mcp/server.

# Limits

|                                                                 | Limit                                                        |
| --------------------------------------------------------------- | ------------------------------------------------------------ |
| Documents per job (`num_documents`)                             | 50                                                           |
| Patients per cohort (`size`)                                    | 50                                                           |
| Documents per patient in a cohort (`documents_per_patient.max`) | 50                                                           |
| Patient `narrative`                                             | 4,000 characters                                             |
| Patient age                                                     | 0 to 110                                                     |
| Complexity                                                      | 1 to 10                                                      |
| Active jobs and cohorts (queued and running) per organization   | 10; a cohort counts as one                                   |
| Active cohorts per organization                                 | 2                                                            |
| Submissions per organization                                    | 60 per minute                                                |
| Results                                                         | Each downloadable once, within 24 hours of the job finishing |
| Idempotency keys                                                | Remembered for 24 hours                                      |

A request over a size limit is rejected when you submit, with `422` and a code naming it:
`too_many_documents` or `cohort_too_large`. Other out-of-range values are rejected with
`422 request_validation`. A submission over a rate or concurrency limit is rejected with
`429 rate_limited` and a `Retry-After` header giving the seconds to wait. Resubmitting with
the same `Idempotency-Key` returns the original job and is never limited.

If your workload needs higher limits, contact
[support@emtelligent.com](mailto:support@emtelligent.com).