API reference · Dedicated endpoints
Public catalog models a dedicated endpoint can serve, with the engine used on CPU and on GPU hardware
/v1/endpoint-models- TypeScript
client.dedicatedEndpoints.listDeployableModels()- Python
client.dedicated_endpoints.list_deployable_models()- CLI
hayonix endpoints models
Available public chat, completion, embedding and rerank models whose weights can be deployed. Pass a listed model as a deployment's model; to serve other weights, use a Hugging Face source instead.
Project API key (Authorization: Bearer sk_…), or a console session. Requires the dedicated_endpoint: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/endpoint-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 a page of results — Deployable models
The items of this page.
ShowHide 8 fields of
dataobjectstringrequiredAlways `deployable_model`: the type of this object
One of
deployable_modelmodelstringrequiredModel ID (`publisher/name`)
display_namestringrequiredName to show people
typestringrequiredWhat the model does
One of
chatcompletionembeddingrerankpublisherstring | nullrequiredWho published the model; null when not recorded
context_lengthinteger | nullrequiredThe model's context length in tokens; null when not known
weightsobjectrequiredThe weights a deployment of this model serves
ShowHide 2 fields of
weightsrepositorystringrequiredThe Hugging Face repository the weights come from
filestring | nullrequiredThe weights file or quantisation tag used; null when the whole repository is used
enginesobjectrequiredThe engine chosen by default on each kind of hardware
ShowHide 2 fields of
enginescpustring | nullrequiredThe engine used on CPU hardware (null: GPU only)
One of
llama_cppteivllmgpustringrequiredThe engine used on GPU hardware
One of
llama_cppteivllm
next_cursorstring | nullrequiredPass as `cursor` for the next page; null on the last page.
Example response
{
"data": [
{
"object": "deployable_model",
"model": "qwen/qwen2.5-0.5b-instruct",
"display_name": "string",
"type": "chat",
"publisher": "string",
"context_length": 1,
"weights": {
"repository": "string",
"file": "string"
},
"engines": {
"cpu": "llama_cpp",
"gpu": "llama_cpp"
}
}
],
"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. |