API reference · Evaluations
List the models this project can use as a judge or to generate candidates
/v1/evaluations/models- TypeScript
client.evaluations.listModels()- Python
client.evaluations.list_models()- CLI
hayonix evaluations models
Chat models the project can call that have batch prices (every evaluation call is charged at batch prices), the project’s fine-tuned models, and its dedicated endpoints’ models (paid by replica time).
Project API key (Authorization: Bearer sk_…), or a console session. Requires the evaluation:read permission (a key's scope, or a role that includes it).
Examples
The samples read API_KEY and API_BASE_URL from the environment (see Setup). Values are examples.
curl -sS "$API_BASE_URL/evaluations/models" \
-H "Authorization: Bearer $API_KEY"Request
| Header | Required | Description |
|---|---|---|
Authorization | yes | Bearer and your API key. The key implies its project. |
X-Project-Id | session only | The project to act in, for console sessions. Requests with an API key leave it out. |
Query parameters
limitinteger1–200, default 50
1–200
cursorstring`next_cursor` of the previous page
up to 200 characters
Response
200 EvaluationModelList — Usable models
The items of this page.
ShowHide 8 fields of
dataidstringrequiredUnique ID (`mdl_…`)
ID with prefix mdl_
objectstringrequiredAlways `evaluation_model`: the type of this object
One of
evaluation_modelmodelstringrequiredThe API name to use as `judge.model` or a candidate `model`
display_namestringrequiredName to show people
sourcestringrequiredA public catalog model, a fine-tuned model, a dedicated endpoint, or another project model
One of
catalogfine_tuneddedicated_endpointprojectbillingstringrequired`per_token`: each call is charged per token at batch prices; `replica_time`: a dedicated endpoint, paid by its replica time instead
One of
per_tokenreplica_timepriceobject | nullrequiredBatch price, nano-USD per 1M tokens (null: paid by replica time)
ShowHide 2 fields of
priceinputstring | nullrequirednano-USD per 1M prompt tokens; null when the model has no input price
outputstring | nullrequirednano-USD per 1M generated tokens; null when the model has no output price
servingbooleanrequiredWhether a replica is ready to serve the model right now; calls to a model nobody serves wait, then fail
next_cursorstring | nullrequiredPass as `cursor` for the next page; null on the last page.
Example response
{
"data": [
{
"id": "mdl_01jc5zq4m8k3v6x9t2w7r0b1e4",
"object": "evaluation_model",
"model": "string",
"display_name": "string",
"source": "catalog",
"billing": "per_token",
"price": {
"input": "string",
"output": "string"
},
"serving": true
}
],
"next_cursor": "string"
}Errors
Errors use the standard envelope. What this operation can answer:
| Status | Type | When |
|---|---|---|
400 | invalid_request_error | A parameter or body field is missing or not allowed; param names it. |
401 | authentication_error | The key or session is missing, revoked or expired. |
403 | permission_error | The credential lacks the permission this needs, or the organization is suspended. |
429 | rate_limit_error rate_limited | Too many requests; retry after retry-after seconds. |