Skip to content
sgp
API Reference

Models

Create a custom model
POST/v5/models
List custom models
GET/v5/models
Update a custom model
PATCH/v5/models/{model_id}
Delete a custom model
DELETE/v5/models/{model_id}
Get a custom model
GET/v5/models/{model_id}
ModelsExpand Collapse
InferenceModel object { id, created_at, created_by_identity_type, 10 more }
id: string

The unique identifier of the entity.

created_at: string

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

formatdate-time
created_by_identity_type: "user" or "service_account"

The type of identity that created the entity.

One of the following:
"user"
"service_account"
created_by_user_id: string

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: string
status: "failed" or "ready" or "deploying" or "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 map[unknown]
object: optional "model"
status_reason: optional string
vendor_configuration: optional LaunchVendorConfiguration { model_image, model_infra } or LlmEngineVendorConfiguration { model, chat_template_override, checkpoint_path, 20 more }
One of the following:
LaunchVendorConfiguration object { model_image, model_infra }
model_image: object { command, registry, repository, 9 more }
command: array of string
registry: string
repository: string
tag: string
env_vars: optional map[unknown]
healthcheck_route: optional string
predict_route: optional string
readiness_delay: optional number
request_schema: optional map[unknown]
response_schema: optional map[unknown]
streaming_command: optional array of string
streaming_predict_route: optional string
model_infra: object { cpus, endpoint_type, gpu_type, 9 more }
cpus: optional string or number
One of the following:
string
number
endpoint_type: optional "async" or "sync" or "streaming"
One of the following:
"async"
"sync"
"streaming"
gpu_type: optional "nvidia-tesla-t4" or "nvidia-ampere-a10" or "nvidia-ampere-a100" or 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 number
high_priority: optional boolean
labels: optional map[string]
max_workers: optional number
memory: optional string
min_workers: optional number
per_worker: optional number
public_inference: optional boolean
storage: optional string
LlmEngineVendorConfiguration object { model, chat_template_override, checkpoint_path, 20 more }
model: string
chat_template_override: optional string
checkpoint_path: optional string
cpus: optional number
default_callback_url: optional string
endpoint_type: optional string
gpu_type: optional string
gpus: optional number
high_priority: optional boolean
inference_framework: optional string
inference_framework_image_tag: optional string
labels: optional map[string]
max_workers: optional number
memory: optional string
min_workers: optional number
nodes_per_worker: optional number
num_shards: optional number
per_worker: optional number
post_inference_hooks: optional array of string
public_inference: optional boolean
quantize: optional string
source: optional string
storage: optional string
InferenceModelAvailability = "unknown" or "available" or "unavailable"
One of the following:
"unknown"
"available"
"unavailable"
InferenceModelType = "generic" or "completion" or "chat_completion"
One of the following:
"generic"
"completion"
"chat_completion"
LaunchVendorConfiguration object { model_image, model_infra }
model_image: object { command, registry, repository, 9 more }
command: array of string
registry: string
repository: string
tag: string
env_vars: optional map[unknown]
healthcheck_route: optional string
predict_route: optional string
readiness_delay: optional number
request_schema: optional map[unknown]
response_schema: optional map[unknown]
streaming_command: optional array of string
streaming_predict_route: optional string
model_infra: object { cpus, endpoint_type, gpu_type, 9 more }
cpus: optional string or number
One of the following:
string
number
endpoint_type: optional "async" or "sync" or "streaming"
One of the following:
"async"
"sync"
"streaming"
gpu_type: optional "nvidia-tesla-t4" or "nvidia-ampere-a10" or "nvidia-ampere-a100" or 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 number
high_priority: optional boolean
labels: optional map[string]
max_workers: optional number
memory: optional string
min_workers: optional number
per_worker: optional number
public_inference: optional boolean
storage: optional string
LlmEngineVendorConfiguration object { model, chat_template_override, checkpoint_path, 20 more }
model: string
chat_template_override: optional string
checkpoint_path: optional string
cpus: optional number
default_callback_url: optional string
endpoint_type: optional string
gpu_type: optional string
gpus: optional number
high_priority: optional boolean
inference_framework: optional string
inference_framework_image_tag: optional string
labels: optional map[string]
max_workers: optional number
memory: optional string
min_workers: optional number
nodes_per_worker: optional number
num_shards: optional number
per_worker: optional number
post_inference_hooks: optional array of string
public_inference: optional boolean
quantize: optional string
source: optional string
storage: optional string
ModelDeleteResponse object { id, deleted, object }
id: string
deleted: boolean
object: optional "model"