API Reference

Models

Copy Markdown

Open in Claude

Open in ChatGPT

Open in Cursor

---

Copy Markdown

View as Markdown

Get a custom model

models.retrieve(strmodel_id) -> InferenceModel

GET/v5/models/{model_id}

Retrieve a single custom model record by its ID.

Returns the model record — including its vendor, configuration, and current deployment status — for a model managed through this API and owned by the caller’s account. This is distinct from GET /v5/chat/completions/models, which lists the models available to call for chat completions rather than returning a single managed record.

ParametersExpand Collapse

model_id: str

ReturnsExpand Collapse

class InferenceModel: …

id: str

The unique identifier of the entity.

created_at: datetime

The date and time when the entity was created in ISO format.

formatdate-time

created_by_identity_type: Literal["user", "service_account"]

The type of identity that created the entity.

One of the following:

"user"

"service_account"

created_by_user_id: str

The user who originally created the entity.

model_type: InferenceModelType

One of the following:

"generic"

"completion"

"chat_completion"

model_vendor: InferenceModelVendor

One of the following:

"openai"

"cohere"

"vertex_ai"

"anthropic"

"azure"

"gemini"

"launch"

"llmengine"

"model_zoo"

"bedrock"

"xai"

"fireworks_ai"

name: str

status: Literal["failed", "ready", "deploying", "deployment_timeout"]

One of the following:

"failed"

"ready"

"deploying"

"deployment_timeout"

model_availability: Optional[InferenceModelAvailability]

One of the following:

"unknown"

"available"

"unavailable"

model_metadata: Optional[Dict[str, object]]

object: Optional[Literal["model"]]

status_reason: Optional[str]

vendor_configuration: Optional[VendorConfiguration]

One of the following:

class LaunchVendorConfiguration: …

model_image: ModelImage

command: List[str]

registry: str

repository: str

tag: str

env_vars: Optional[Dict[str, object]]

healthcheck_route: Optional[str]

predict_route: Optional[str]

readiness_delay: Optional[int]

request_schema: Optional[Dict[str, object]]

response_schema: Optional[Dict[str, object]]

streaming_command: Optional[List[str]]

streaming_predict_route: Optional[str]

model_infra: ModelInfra

cpus: Optional[Union[str, int, null]]

One of the following:

str

int

endpoint_type: Optional[Literal["async", "sync", "streaming"]]

One of the following:

"async"

"sync"

"streaming"

gpu_type: Optional[Literal["nvidia-tesla-t4", "nvidia-ampere-a10", "nvidia-ampere-a100", 4 more]]

One of the following:

"nvidia-tesla-t4"

"nvidia-ampere-a10"

"nvidia-ampere-a100"

"nvidia-ampere-a100e"

"nvidia-hopper-h100"

"nvidia-hopper-h100-1g20gb"

"nvidia-hopper-h100-3g40gb"

gpus: Optional[int]

high_priority: Optional[bool]

labels: Optional[Dict[str, str]]

max_workers: Optional[int]

memory: Optional[str]

min_workers: Optional[int]

per_worker: Optional[int]

public_inference: Optional[bool]

storage: Optional[str]

class LlmEngineVendorConfiguration: …

model: str

chat_template_override: Optional[str]

checkpoint_path: Optional[str]

cpus: Optional[int]

default_callback_url: Optional[str]

endpoint_type: Optional[str]

gpu_type: Optional[str]

gpus: Optional[int]

high_priority: Optional[bool]

inference_framework: Optional[str]

inference_framework_image_tag: Optional[str]

labels: Optional[Dict[str, str]]

max_workers: Optional[int]

memory: Optional[str]

min_workers: Optional[int]

nodes_per_worker: Optional[int]

num_shards: Optional[int]

per_worker: Optional[int]

post_inference_hooks: Optional[List[str]]

public_inference: Optional[bool]

quantize: Optional[str]

source: Optional[str]

storage: Optional[str]

Get a custom model

Python

HTTP

TypeScript

Python

Go

import os
from scale_gp_beta import SGPClient

client = SGPClient(
    api_key=os.environ.get("SGP_API_KEY"),  # This is the default and can be omitted
)
inference_model = client.models.retrieve(
    "model_id",
)
print(inference_model.id)

200 example

{
  "id": "id",
  "created_at": "2019-12-27T18:11:19.117Z",
  "created_by_identity_type": "user",
  "created_by_user_id": "created_by_user_id",
  "model_type": "generic",
  "model_vendor": "openai",
  "name": "name",
  "status": "failed",
  "model_availability": "unknown",
  "model_metadata": {
    "foo": "bar"
  },
  "object": "model",
  "status_reason": "status_reason",
  "vendor_configuration": {
    "model_image": {
      "command": [
        "string"
      ],
      "registry": "registry",
      "repository": "repository",
      "tag": "tag",
      "env_vars": {
        "foo": "bar"
      },
      "healthcheck_route": "healthcheck_route",
      "predict_route": "predict_route",
      "readiness_delay": 0,
      "request_schema": {
        "foo": "bar"
      },
      "response_schema": {
        "foo": "bar"
      },
      "streaming_command": [
        "string"
      ],
      "streaming_predict_route": "streaming_predict_route"
    },
    "model_infra": {
      "cpus": "string",
      "endpoint_type": "async",
      "gpu_type": "nvidia-tesla-t4",
      "gpus": 0,
      "high_priority": true,
      "labels": {
        "foo": "string"
      },
      "max_workers": 0,
      "memory": "memory",
      "min_workers": 0,
      "per_worker": 0,
      "public_inference": true,
      "storage": "storage"
    }
  }
}

Returns Examples

200 example

{
  "id": "id",
  "created_at": "2019-12-27T18:11:19.117Z",
  "created_by_identity_type": "user",
  "created_by_user_id": "created_by_user_id",
  "model_type": "generic",
  "model_vendor": "openai",
  "name": "name",
  "status": "failed",
  "model_availability": "unknown",
  "model_metadata": {
    "foo": "bar"
  },
  "object": "model",
  "status_reason": "status_reason",
  "vendor_configuration": {
    "model_image": {
      "command": [
        "string"
      ],
      "registry": "registry",
      "repository": "repository",
      "tag": "tag",
      "env_vars": {
        "foo": "bar"
      },
      "healthcheck_route": "healthcheck_route",
      "predict_route": "predict_route",
      "readiness_delay": 0,
      "request_schema": {
        "foo": "bar"
      },
      "response_schema": {
        "foo": "bar"
      },
      "streaming_command": [
        "string"
      ],
      "streaming_predict_route": "streaming_predict_route"
    },
    "model_infra": {
      "cpus": "string",
      "endpoint_type": "async",
      "gpu_type": "nvidia-tesla-t4",
      "gpus": 0,
      "high_priority": true,
      "labels": {
        "foo": "string"
      },
      "max_workers": 0,
      "memory": "memory",
      "min_workers": 0,
      "per_worker": 0,
      "public_inference": true,
      "storage": "storage"
    }
  }
}