Models
List Models
Question Sets
Dataset Items
Evaluations
Evaluation Items
Models
List Models
GET
/
v5
/
models
curl --request GET \
--url https://api.egp.scale.com/v5/models \
--header 'x-api-key: <api-key>'
{
"object": "list",
"items": [
{
"id": "<string>",
"object": "model",
"name": "<string>",
"model_type": "generic",
"model_vendor": "openai",
"vendor_configuration": {
"model_image": {
"registry": "<string>",
"repository": "<string>",
"tag": "<string>",
"predict_route": "/predict",
"command": [
"<string>"
],
"streaming_predict_route": "<string>",
"streaming_command": [
"<string>"
],
"request_schema": {},
"response_schema": {},
"env_vars": {},
"readiness_delay": 120,
"healthcheck_route": "/readyz"
},
"model_infra": {
"endpoint_type": "sync",
"cpus": "<string>",
"gpus": 0,
"gpu_type": "nvidia-tesla-t4",
"memory": "8Gi",
"storage": "16Gi",
"min_workers": 0,
"max_workers": 1,
"per_worker": 10,
"high_priority": false,
"labels": {},
"public_inference": false
}
},
"status": "failed",
"model_metadata": {},
"display_name": "<string>",
"description": "<string>",
"created_at": "2023-11-07T05:31:56Z",
"created_by_user_id": "<string>"
}
],
"limit": 100,
"total": 123,
"has_more": true
}
Authorizations
Query Parameters
Available options:
openai
, cohere
, vertex_ai
, anthropic
, azure
, gemini
, launch
, llmengine
, model_zoo
, bedrock
, xai
Required range:
1 <= x <= 1000
Response
200
application/json
Successful Response
Available options:
generic
, completion
, chat_completion
Available options:
openai
, cohere
, vertex_ai
, anthropic
, azure
, gemini
, launch
, llmengine
, model_zoo
, bedrock
, xai
Available options:
failed
, ready
, deploying
Available options:
model
Available options:
async
, sync
, streaming
Available options:
nvidia-tesla-t4
, nvidia-ampere-a10
, nvidia-ampere-a100
, nvidia-ampere-a100e
, nvidia-hopper-h100
, nvidia-hopper-h100-1g20gb
, nvidia-hopper-h100-3g40gb
The total of items that match the query. This is greater than or equal to the number of items returned.
Whether there are more items left to be fetched.
Available options:
list
The maximum number of items to return.
curl --request GET \
--url https://api.egp.scale.com/v5/models \
--header 'x-api-key: <api-key>'
{
"object": "list",
"items": [
{
"id": "<string>",
"object": "model",
"name": "<string>",
"model_type": "generic",
"model_vendor": "openai",
"vendor_configuration": {
"model_image": {
"registry": "<string>",
"repository": "<string>",
"tag": "<string>",
"predict_route": "/predict",
"command": [
"<string>"
],
"streaming_predict_route": "<string>",
"streaming_command": [
"<string>"
],
"request_schema": {},
"response_schema": {},
"env_vars": {},
"readiness_delay": 120,
"healthcheck_route": "/readyz"
},
"model_infra": {
"endpoint_type": "sync",
"cpus": "<string>",
"gpus": 0,
"gpu_type": "nvidia-tesla-t4",
"memory": "8Gi",
"storage": "16Gi",
"min_workers": 0,
"max_workers": 1,
"per_worker": 10,
"high_priority": false,
"labels": {},
"public_inference": false
}
},
"status": "failed",
"model_metadata": {},
"display_name": "<string>",
"description": "<string>",
"created_at": "2023-11-07T05:31:56Z",
"created_by_user_id": "<string>"
}
],
"limit": 100,
"total": 123,
"has_more": true
}