Get customers
Answer customers
Work for you
Reach people
Give agents tools
Run and ship
Deploy models, run inference, manage fine-tuning jobs and files with Scale Launch
List model bundles owned by the connected account.
2 fields
Read a model bundle's deployment metadata.
1 field
Find the latest bundle for a model name.
List model deployments owned by the connected account.
Read one model endpoint's configuration and status.
Deploy a bundle on provisioned workers. This allocates paid compute.
13 fields
Change a deployment's bundle, compute settings, labels or metadata.
12 fields
Delete a model deployment and stop its workers.
Restart the workers serving a model deployment.
Submit JSON model inputs for asynchronous inference.
Poll asynchronous inference status and retrieve the JSON result.
Run synchronous inference with JSON model inputs.
4 fields
List the connected account's fine-tuning jobs.
Start a paid fine-tuning job using an existing training file.
5 fields
Read fine-tuning progress and the resulting model name.
Cancel a fine-tuning job.
Read a fine-tuning job's progress events.
List file IDs, names and sizes for the connected account.
Read file metadata without downloading file contents.
Delete a stored file.
