Platform API reference: endpoints, methods, and paths

Every Kite Platform API endpoint at a glance — augmentation, training, and account routes, with methods, paths, and links to the OpenAPI spec.

All endpoints are under https://api.kiteml.com/v1. Every request needs Authorization: Bearer kite_…, and should send Kite-Version: 2026-09-27 (see versions). This page is the map; each endpoint’s own page, with every parameter, response field, and error, is under the API reference tab. Both are generated from the OpenAPI document at https://api.kiteml.com/v1/openapi.json, so they describe exactly what the API does.

Augmentations

Method	Path	Description
POST	/v1/augmentations	Start a run (source, instructions, model, reference_images, config, output)
POST	/v1/augmentations/estimate	Estimate the token cost of a run before starting it (model: relight or video)
GET	/v1/augmentations/:id	Status, progress, and — when done — output files
GET	/v1/augmentations	List your runs
POST	/v1/augmentations/:id/cancel	Cancel a running augmentation

See Augmentations for the full lifecycle, request body, and response shapes.

Account

Method	Path	Description
GET	/v1/keys/me	Identity and scopes for the current API key
GET	/v1/usage	Token usage over a date range, grouped by resource
GET	/v1/credits	Current credit balance

Training runs

Method	Path	Description
POST	/v1/training_runs	Start a run per policy (dataset, policies, hardware_tier, config)
POST	/v1/training_runs/estimate	Estimate the token cost of a run before starting it
GET	/v1/training_runs/:id	Status, phase, live metrics, and output
GET	/v1/training_runs	List your runs
GET	/v1/training_runs/:id/logs	Tail the trainer’s output
GET	/v1/training_runs/:id/checkpoints	List the checkpoints a run saved
GET	/v1/training_runs/:id/checkpoints/:step/download	Download one checkpoint as a ZIP of its pretrained_model/
POST	/v1/training_runs/:id/cancel	Cancel a run and release its GPU

See Training runs for the full lifecycle, request body, and response shapes.

Twins

Private beta — see Twins.

Method	Path	Description
POST	/v1/twins/validate	Check a dataset for free: cameras, the one that seeds the room, and a time estimate
POST	/v1/twins	Build a twin from one episode (source)
GET	/v1/twins/:id	Status, stages with their measurements, and — when done — the scene download
GET	/v1/twins	List your twins
GET	/v1/twins/:id/files	Every file in a finished twin’s archive, with size and SHA-256
GET	/v1/twins/:id/archive	The scene as one .tar.gz (redirects to a signed link)
POST	/v1/twins/:id/cancel	Stop a twin that’s building
POST	/v1/twins/:id/resume	Continue a failed or canceled twin from the stages it finished

RL runs

See RL runs for a worked example, from the request to the policy running in MuJoCo.

Method	Path	Description
GET	/v1/rl_runs/catalog	Robots, objectives with every parameter and its bounds, hardware tiers, engines
POST	/v1/rl_runs/plan	A task spec from a plain-English description
POST	/v1/rl_runs/validate	Check a spec for free: compile it and roll canned policies through it
POST	/v1/rl_runs/estimate	Minutes and tokens for a spec
POST	/v1/rl_runs	Train: one run per seed
GET	/v1/rl_runs/:id	Status and live metrics; once packaged, the verdict and the outputs
GET	/v1/rl_runs	List your RL runs
GET	/v1/rl_runs/:id/metrics	The training curve, reward by term
GET	/v1/rl_runs/:id/checkpoints	Saved iterations; each downloads as ONNX or as the training checkpoint
GET	/v1/rl_runs/:id/report	The verdict, its checks, and the judge’s read of the clip
GET	/v1/rl_runs/:id/files	Every file in the bundle, with size and SHA-256
GET	/v1/rl_runs/:id/archive	The bundle as one zip
POST	/v1/rl_runs/:id/cancel	Stop a run; one that has trained keeps its policy

Catalog

Method	Path	Description
GET	/v1/training_policies	Policy types you can train, and the GPU each one needs
GET	/v1/hardware_tiers	GPU tiers, with the token rate each one bills at
POST	/v1/datasets/inspect	Check a dataset is trainable and read its camera keys

Operations and webhooks

Method	Path	Description
GET	/v1/operations/:id	Uniform status for any run, by id prefix (aug_, trn_, twin_)
POST	/v1/webhook_endpoints	Register a receiver for run events
GET	/v1/webhook_endpoints	List your receivers
DELETE	/v1/webhook_endpoints/:id	Remove a receiver
GET	/v1/events	The durable event log, so polling is always a fallback

Events: augmentation.completed, augmentation.failed, augmentation.canceled, training_run.completed, training_run.failed, training_run.canceled, twin.completed, twin.failed, twin.canceled.

Evaluate

Coming soon. Simulation evaluation endpoints aren’t on /v1 yet. Evaluation runs are available today from the dashboard and the Kite CLI.

The interactive reference at api.kiteml.com/v1/docs is generated from the same OpenAPI spec the API is built on, so it’s always in sync with production.

Every long-running resource answers to GET /v1/operations/:id, whatever its id prefix. If you poll more than one kind of run, write that loop once against operations rather than one loop per resource — the status vocabulary is the same for all of them.