Skip to main content
POST
/
v5
/
models
Create Model
curl --request POST \
  --url https://api.egp.scale.com/v5/models \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '{
  "name": "<string>",
  "model_type": "generic",
  "model_vendor": "launch",
  "model_metadata": {},
  "on_conflict": "error",
  "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
    }
  }
}'
{
  "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": {},
  "model_availability": "unknown",
  "created_at": "2023-11-07T05:31:56Z",
  "created_by_user_id": "<string>",
  "created_by_identity_type": "user"
}

Authorizations

​
x-api-key
string
header
required

Headers

​
x-selected-account-id
string | null

Body

application/json
  • LaunchModelCreateRequest
  • LLMEngineModelCreateRequest
​
name
string
required

Unique name to reference your model

​
vendor_configuration
object
required
​
model_type
string
default:generic
Allowed value: "generic"
​
model_vendor
string
default:launch
Allowed value: "launch"
​
model_metadata
object
​
on_conflict
enum<string>
default:error
Available options:
error,
update

Response

Successful Response

​
id
string
required
​
name
string
required
​
model_type
enum<string>
required
Available options:
generic,
completion,
chat_completion
​
model_vendor
enum<string>
required
Available options:
openai,
cohere,
vertex_ai,
anthropic,
azure,
gemini,
launch,
llmengine,
model_zoo,
bedrock,
xai,
fireworks_ai
​
status
enum<string>
required
Available options:
failed,
ready,
deploying
​
created_at
string<date-time>
required
​
created_by_user_id
string
required
​
created_by_identity_type
enum<string>
required
Available options:
user,
service_account
​
object
string
default:model
Allowed value: "model"
​
vendor_configuration
object
  • LaunchVendorConfiguration
  • LLMEngineVendorConfiguration
​
model_metadata
object
​
model_availability
enum<string>
Available options:
unknown,
available,
unavailable