# Impulse Labs

## Docs

- [Create API Key](https://docs.impulselabs.ai/api-reference/api-keys/create.md): Create a new API key for the authenticated user. The raw key is returned once and cannot be retrieved again.
- [List API Keys](https://docs.impulselabs.ai/api-reference/api-keys/list.md): List all API keys for the authenticated user. Raw key values are never returned — only metadata.
- [Revoke API Key](https://docs.impulselabs.ai/api-reference/api-keys/revoke.md): Permanently revoke an API key. Any requests using the revoked key will immediately return 401.
- [Errors](https://docs.impulselabs.ai/api-reference/errors.md): HTTP status codes and error response shapes returned by the Impulse Labs API
- [Run Inference](https://docs.impulselabs.ai/api-reference/inference/run.md): Send input features to a deployed model and receive a prediction. The model container must be in ACTIVE status.
- [Deployment Status](https://docs.impulselabs.ai/api-reference/inference/status.md): Check whether a model deployment is ready to receive inference requests.
- [Rate Limits](https://docs.impulselabs.ai/api-reference/rate-limits.md): Per-plan request limits and how to handle 429 responses
- [Authentication](https://docs.impulselabs.ai/authentication.md): Authenticate API requests with an Impulse Labs API key
- [GPU Runtime Cost Anomaly Runbook](https://docs.impulselabs.ai/gpu-operations/cost-anomaly.md): Detection, investigation, and remediation procedures for unexpected GPU cost events
- [GPU Runtime Deployment Runbook](https://docs.impulselabs.ai/gpu-operations/deployment.md): Step-by-step procedures for deploying and rolling back the GPU Sandbox execution runtime
- [GPU Runtime DLQ Recovery Runbook](https://docs.impulselabs.ai/gpu-operations/dlq-recovery.md): Procedures for inspecting, replaying, and recovering messages from the GPU Runtime dead-letter queue
- [GPU Runtime Failure Recovery Runbook](https://docs.impulselabs.ai/gpu-operations/failure-recovery.md): Recovery procedures for scheduler outages, Vertex quota exhaustion, artifact upload failures, preemption storms, and Pub/Sub consumer failures
- [GPU Runtime Incident Response Checklist](https://docs.impulselabs.ai/gpu-operations/incident-response.md): Production operations checklist for GPU Runtime incidents — containment, triage, service recovery, artifact validation, and postmortem requirements
- [GPU Runtime Quota Exhaustion Runbook](https://docs.impulselabs.ai/gpu-operations/quota-exhaustion.md): Detection, containment, and recovery procedures for Vertex AI GPU quota exhaustion events
- [Introduction](https://docs.impulselabs.ai/introduction.md): Use models you train in the Impulse AI dashboard via a simple REST API
- [Quickstart](https://docs.impulselabs.ai/quickstart.md): Train a model in the dashboard and get your first inference in under 5 minutes

## OpenAPI Specs

- [users](https://docs.impulselabs.ai/users.yml)
- [usage](https://docs.impulselabs.ai/usage.yml)
- [models](https://docs.impulselabs.ai/models.yml)
- [fine-tuning](https://docs.impulselabs.ai/fine-tuning.yml)
- [datasets](https://docs.impulselabs.ai/datasets.yml)
- [billing](https://docs.impulselabs.ai/billing.yml)
- [api-keys](https://docs.impulselabs.ai/api-keys.yml)
- [openapi](https://docs.impulselabs.ai/api-reference/openapi.json)

## Optional

- [Impulse AI App](https://app.impulselabs.ai)
- [Blog](https://www.impulselabs.ai/blog)