Skip to content
sgp
API Reference

Models

Create a custom model
models.create(ModelCreateParams**kwargs) -> InferenceModel
POST/v5/models
List custom models
models.list(ModelListParams**kwargs) -> SyncCursorPage[InferenceModel]
GET/v5/models
Update a custom model
models.update(strmodel_id, ModelUpdateParams**kwargs) -> InferenceModel
PATCH/v5/models/{model_id}
Delete a custom model
models.delete(strmodel_id) -> ModelDeleteResponse
DELETE/v5/models/{model_id}
Get a custom model
models.retrieve(strmodel_id) -> InferenceModel
GET/v5/models/{model_id}
ModelsExpand 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]
Literal["unknown", "available", "unavailable"]
One of the following:
"unknown"
"available"
"unavailable"
Literal["generic", "completion", "chat_completion"]
One of the following:
"generic"
"completion"
"chat_completion"
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]
class ModelDeleteResponse: …
id: str
deleted: bool
object: Optional[Literal["model"]]