Current - 2026/07
Endpoint
GET
/v1/stable/evaluation

Returns every evaluation in the project. An evaluation is a criterion a model scores past conversations against. The call takes no paging parameters, so one request yields the whole set.

Request
Response

Authentication

Authorization
string
header
required

Voiceflow bearer token

Query parameters

projectID
string
required

The ID of the project to operate on.

Response

200 - application/json

Returns every evaluation defined on the project, each with the criteria it judges transcripts against, its result type, whether it runs automatically on new transcripts, and its average cost per run.

evaluations
object[]
required
StableEvaluation — see its attributes above
Endpoint
POST
/v1/stable/evaluation

Adds a evaluation to the project, a criterion a model scores past conversations against. The response carries the ID that later calls address it by.

Request
Response

Authentication

Authorization
string
header
required

Voiceflow bearer token

Query parameters

projectID
string
required

The ID of the project to operate on.

Request body

Response

201 - application/json

Creates the evaluation and returns it with its assigned id. No transcript is scored yet: results come from running it against a transcript, or automatically on new transcripts when enabled is true.

evaluation
object
required
StableEvaluation — see its attributes above
Current - 2026/07
Endpoint
GET
/v1/stable/evaluation/{evaluationID}

Returns a single evaluation by ID, with the fields that define it. An evaluation is a criterion a model scores past conversations against.

Request
Response

Authentication

Authorization
string
header
required

Voiceflow bearer token

Path parameters

evaluationID
string
required

The ID of the evaluation to operate on.

Query parameters

projectID
string
required

The ID of the project to operate on.

Response

200 - application/json

Returns one evaluation in full: the criteria prompts for its result type, the model settings the evaluator judges with, and whether it is one of the built-in defaults.

evaluation
object
required
StableEvaluation — see its attributes above
Current - 2026/07
Endpoint
PATCH
/v1/stable/evaluation/{evaluationID}

Changes an existing evaluation in place. The response carries only a confirmation message, so refetch the evaluation to read its new values.

Request
Response

Authentication

Authorization
string
header
required

Voiceflow bearer token

Path parameters

evaluationID
string
required

The ID of the evaluation to operate on.

Query parameters

projectID
string
required

The ID of the project to operate on.

Request body

Response

200 - application/json

Confirms the evaluation's name, criteria, result type, or enabled state were updated. The body is a message only, so refetch the evaluation to read its stored definition.

message
string
required

A human-readable message confirming the update.

Current - 2026/07
Endpoint
DELETE
/v1/stable/evaluation/{evaluationID}

Deletes a single evaluation by ID. An evaluation is a criterion a model scores past conversations against. The response carries only a confirmation message, so refetch the evaluations to see what is left.

Request
Response

Authentication

Authorization
string
header
required

Voiceflow bearer token

Path parameters

evaluationID
string
required

The ID of the evaluation to operate on.

Query parameters

projectID
string
required

The ID of the project to operate on.

Response

200 - application/json

Confirms the evaluation was removed from the project. The body carries a message only, so drop any cached copy of the project's evaluations.

message
string
required

A human-readable message confirming the deletion.

Current - 2026/07
Endpoint
POST
/v1/stable/evaluation/{evaluationID}/run

Scores one finished conversation against an evaluation. The response carries the verdict together with the reasoning behind it, so a low score says why.

Request
Response

Authentication

Authorization
string
header
required

Voiceflow bearer token

Path parameters

evaluationID
string
required

The ID of the evaluation to operate on.

Query parameters

projectID
string
required

The ID of the project to operate on.

Request body

transcriptID
string
required

The ID of the transcript to run the evaluation against.

Response

201 - application/json

Scores the transcript named in the body against this evaluation and returns the result: the value the evaluator produced, typed to match the evaluation, the reason behind it, and the LLM cost the run incurred.

result
object
required
StableEvaluationResult — see its attributes above
Endpoint
POST
/v1/stable/evaluation/queue-runs

Queue evaluations against transcripts.

Request
Response

Authentication

Authorization
string
header
required

Voiceflow bearer token

Query parameters

projectID
string
required

The ID of the project to operate on.

Request body

evaluationIDs
string[]
required

The evaluations to run, 1 to 10. Every evaluation runs against every transcript.

Minimum items: 1 · Maximum items: 10
transcriptIDs
string[]
required

The transcripts to score, 1 to 100.

Minimum items: 1 · Maximum items: 100

Response

202 - application/json
evaluationCount
integer
required

Evaluation runs queued across all transcripts.

Minimum: -9007199254740991 · Maximum: 9007199254740991
transcriptCount
integer
required

Transcripts queued for at least one evaluation. Lower than the number sent when some were skipped: another project, not ended yet, or expired.

Minimum: -9007199254740991 · Maximum: 9007199254740991
warning
object

Set when the evaluation quota made the queue skip transcripts; it names them.

Schemas

Use the up and down arrow keys to select a result, Enter to open it, and Escape to close the search.