Skip to main content

AI Models

AI Models are the model catalog. Use this resource to register third-party or self-hosted models, link a provider key (via apiKeyId), deploy/start/stop self-hosted models, and read status, logs, and permissions.

Access it as client.ai.models on a Strongly client, or the same path on AsyncStrongly with await. All methods exist on both with identical signatures.

Quick start​

from strongly import Strongly

client = Strongly()

# List (auto-paginates as you iterate)  # filters: search, type, status, provider, model_type
for model in client.ai.models.list():
    print(model.id)

# Create
created = client.ai.models.create(
    name="gpt-4o",
    type="third-party",
    provider="openai",
    vendor_model_id="gpt-4o",
    model_type="chat",
)
print(created.id)

# Read it back
fetched = client.ai.models.retrieve(created.id)

# Delete (returns None; raises on failure)
client.ai.models.delete(created.id)

Methods​

Core​

list​

list(*, search: Optional[str] = None, type: Optional[str] = None, status: Optional[str] = None, provider: Optional[str] = None, model_type: Optional[str] = None, limit: Optional[int] = None) -> SyncPaginator[AIModel]

List AI models with pagination, filtering, and search.

create​

create(*, name: str, type: str, provider: str, vendor_model_id: str, model_type: Optional[str] = None, description: Optional[str] = None, capabilities: Optional[Sequence[str]] = None, max_tokens: Optional[int] = None, context_window: Optional[int] = None, config: Optional[Mapping[str, Any]] = None, **extra) -> AIModel

Create a new AI model.

Args: name: Model display name. type: Model kind (e.g. third-party or self-hosted). provider: Provider name. vendor_model_id: The vendor's model identifier. model_type: Capability class (e.g. chat, embedding, tts). description: Optional description. capabilities: Optional capability tags. max_tokens: Optional max output tokens. context_window: Optional context window size. config: Optional model configuration. **extra: Additional camelCase fields accepted by the create route (e.g. apiKeyId, self-hosted deploy options).

model = client.ai.models.create(
    name="gpt-4o",
    type="third-party",
    provider="openai",
    vendor_model_id="gpt-4o",
    model_type="chat",
    apiKeyId="key_abc123",
)

retrieve​

retrieve(model_id: str) -> AIModel

Get a single AI model by ID.

update​

update(model_id: str, *, name: Optional[str] = None, type: Optional[str] = None, provider: Optional[str] = None, vendor_model_id: Optional[str] = None, model_type: Optional[str] = None, description: Optional[str] = None, capabilities: Optional[Sequence[str]] = None, max_tokens: Optional[int] = None, context_window: Optional[int] = None, config: Optional[Mapping[str, Any]] = None, **extra) -> AIModel

Update an AI model. **extra forwards additional camelCase fields accepted by the update route.

delete​

delete(model_id: str) -> None

Delete an AI model.

Lifecycle & actions​

start​

start(model_id: str) -> Dict[str, Any]

Start an AI model.

stop​

stop(model_id: str) -> Dict[str, Any]

Stop an AI model.

deploy​

deploy(model_id: str, **kwargs) -> Dict[str, Any]

Deploy an AI model.

Sharing & scope​

update_permissions​

update_permissions(model_id: str, *, is_shared: Optional[bool] = None, shared_with: Optional[List[str]] = None) -> Dict[str, Any]

Update model sharing permissions.

Other​

clear_cache​

clear_cache(model_id: str) -> Dict[str, Any]

Clear cached metadata for a model.

list_certified​

list_certified() -> Dict[str, Any]

List Strongly-certified models.

list_prebuilt​

list_prebuilt() -> Dict[str, Any]

List pre-built models available for deployment.

list_providers​

list_providers() -> Dict[str, Any]

List AI providers supported by the gateway.

logs​

logs(model_id: str, *, lines: Optional[int] = None, since: Optional[str] = None, container: Optional[str] = None) -> Dict[str, Any]

Get model logs.

Args: model_id: The model ID. lines: Number of log lines to return. since: ISO date string; return logs since this time. container: Container name to get logs from.

metrics​

metrics(model_id: str) -> Dict[str, Any]

Get model metrics.

options​

options(model_id: str) -> Dict[str, Any]

Get available deploy/runtime options for a model.

overview​

overview() -> AIModelOverview

Get overview stats for AI models.

permissions​

permissions(model_id: str) -> AIModelPermissions

Get model sharing permissions.

status​

status(model_id: str) -> AIModelStatus

Get model deployment status.