Documentation
Run image and video models on dedicated GPUs.
ClockingCloud provisions a GPU, loads your model and gives you an endpoint, an SSH session and a live observability view from one CLI and one console.
Install
brew install clockingcloudThen follow the quickstart to deploy your first instance.
Start
Install the CLI, sign in and deploy your first instance.
- QuickstartGo from a new account to your first generated image and a deployed instance in about ten minutes.
- InstallationInstall, verify, upgrade and remove the ClockingCloud CLI, and where it keeps its files.
- AuthenticationSign in from a laptop, a headless server, or CI/CD, and manage API keys safely.
- ConceptsThe vocabulary and the mental model: instances, models, GPUs, volumes, scale to zero and credits.
Guides
Task-focused walkthroughs for the things you will do most.
- Running modelsGenerate images and video with clockingcloud run: prompts, sizes, seeds, batches, inputs and results.
- Deploying instancesDefine an instance in clockingcloud.yaml, deploy it, scale it, debug it cheaply, and ship it from CI/CD.
- StorageConnect S3, Azure Blob or Google Cloud Storage, or use ClockingCloud Global Volumes, and mount them into instances.
- SSH accessAdd keys, open a shell on a running instance, copy files, and troubleshoot connections.
- ObservabilityLogs, live GPU metrics, request traces, cost per output, and exporting to your monitoring stack.
- BillingPrepaid credits, per-second GPU billing, what is and is not charged, and what happens at zero.
Reference
Exhaustive detail on commands, configuration, the API and limits.
- CLI referenceEvery command, argument and flag, plus global flags, environment variables and exit codes.
- Configuration referenceEvery field of clockingcloud.yaml, with types, defaults, validation rules and a complete example.
- REST APIProvision, start, stop and observe instances and run generations over HTTPS. Mirrors the CLI one for one.
- OpenAPI specThe machine-readable OpenAPI 3.1 description of every /v1 endpoint, with an interactive explorer.
- ModelsSupported image and video models, their IDs, default GPUs and access requirements.
- GPUsThe four GPU types, their memory, and how auto-selection and multi-GPU work.
- ErrorsAPI error codes, HTTP statuses, retry guidance and CLI exit codes.
- LimitsNaming rules, sizes and other limits that apply to your account.
Operate
Billing, security, troubleshooting and frequently asked questions.
Release
What changed in each release.