Code Prediction endpoint

Prediction of codes across many different systems is supported through a single REST endpoint:

POST https://api.{environment}.corti.app/v2/tools/coding/

Pass your clinical context in the request body and receive a structured list of medical codes ready for review.

New to the API? Start with the Quickstart for a hands-on walkthrough including SDK installation and your first coding request.

Request parameters

Parameter	Type	Required	Description
`system`	`string[]`	Yes	One or more coding systems. See Coding Systems for all options and common combinations for recommended pairings.
`context`	`object[]`	Yes	The clinical input to code. Each item is a `text` string or a `documentId` referencing a document stored in Corti.
`filters`	`object[]`	No	Restrict predictions to specific codes or categories. See Code filtering for details.

Response payload

A successful response returns three top-level fields:

codes: the model’s high-confidence predictions. Each entry includes the code, a human-readable display, evidences (the exact passages from the note that support the prediction), and alternatives (other codes the model considered for the same finding). See Codes and candidates for the full structure.
candidates: lower-confidence codes worth reviewing. Intended for coder review rather than automatic assignment.
usageInfo: credits consumed for this request.

Examples

Single coding system

{
  "system": ["icd10cm-outpatient"],
  "context": [
    { "type": "text", "text": "Patient presents with acute otitis media of the right ear." }
  ]
}

Multiple coding systems in one request

The response includes codes from all requested systems in the same codes array, each tagged with its system value:

{
  "system": ["icd10cm-outpatient", "cpt"],
  "context": [
    { "type": "text", "text": "Patient presents with acute otitis media of the right ear." }
  ]
}

Next steps

Code filtering

Restrict which codes the model may predict using the filters field.

Codes and candidates

Learn more about the response structure: codes, candidates, evidences, and alternatives.

Coding Systems

Details on available systems and recommendations of pairings by use case.

Integration Guides

Combine code prediction with agents and client-side content to build coding workflows.

Please contact us if you need help getting started or run into issues with your first request.

Clinical Text Generation

Medical Coding

Clinical Assistant

Request parameters

Response payload

Examples

Next steps

Code filtering

Codes and candidates

Coding Systems

Integration Guides

​Request parameters

​Response payload

​Examples

​Next steps

Code filtering

Codes and candidates

Coding Systems

Integration Guides

Request parameters

Response payload

Examples

Next steps