Cerebras

Delete a model version and its artifacts.

Deploy a model version to a specific endpoint.

List endpoints available to the organization.

List model architectures accessible to an organization.

List model versions for a given model architecture.

Check the status of a deployment on an endpoint.

Get the status of a specific model version.

Update aliases for a model version.

Upload a new model version with weights and metadata.

Delete a file from storage.

List uploaded files.

Retrieve metadata for a specific file.

Download the raw content of a file.

Upload a file for batch processing.

Cancel a batch job in progress.

Create a batch job for batch processing of requests.

List batch jobs for the user.

Get the status and results for a batch job.

List currently available models and essential details.

Fetch details for a specific model.

Discover publicly available Cerebras models without authentication.

Fetch details for a publicly listed Cerebras model.

Generate a chat completion for a multi-turn conversation.

Generate a standard text completion for a given prompt.

Retrieve operational metrics for your organization’s inference endpoints in Prometheus format.