Each deployment has a dedicated subdomain on api.baseten.co for optimized routing.

For models, the endpoints follow this format:

https://model-{model_id}.api.baseten.co/{deployment_type_or_id}/{endpoint}

For chains, the endpoints follow this format:

https://chain-{chain_id}.api.baseten.co/{deployment_type_or_id}/{endpoint}

Where:

  • model_id – The model’s alphanumeric ID (found in your model dashboard).
  • chain_id – The chain’s alphanumeric ID (found in your chain dashboard).
  • deployment_type_or_id – Either development, production, or a specific deployment’s alphanumeric ID.
  • endpoint – The API action, such as predict.

For long-running tasks, the inference API supports asynchronous inference with priority queuing.

Predict endpoints

MethodEndpointDescription
POST/environments/{env_name}/predictCall an environment
POST/development/predictCall the development deployment
POST/deployment/{deployment_id}/predictCall any deployment
POST/deployment/{deployment_id}/async_predictFor Async inference, call any published deployment of your model.
POST/environments/{env_name}/async_predictFor Async inference, Call the deployment associated with the specified environment.
POST/development/async_predictFor Async inference, Call the deployment associated with the specified environment.
DEL/async_request/{request_id}For Async inference, cancel a request

Async status endpoints

MethodEndpointDescription
GET/async_request/{request_id}Get the status of an async request.
GET/environments/{env_name}/async_queue_statusGet the async queue status for a model associated with the specified environment.
GET/development/async_queue_statusGet the status of a development deployment’s async queue.
GET/deployment/{deployment_id}/async_queue_statusGet the status of a deployment’s async queue.

Wake endpoints

MethodEndpointDescription
POST/production/wakeWake the production environment of your model.
POST/development/wakeWake the development deployment of your model.
POST/deployment/{deployment_id}/wakeWake any deployment of your model.

Was this page helpful?