# Lyceum Documentation

## Docs

- [Create Api Key](https://docs.lyceum.technology/api-reference/api-keys/create-api-key.md): Create a new API key for the authenticated user.
- [List Api Keys](https://docs.lyceum.technology/api-reference/api-keys/list-api-keys.md): List all API keys for the authenticated user.
- [Revoke Api Key](https://docs.lyceum.technology/api-reference/api-keys/revoke-api-key.md): Revoke (delete) an API key.
- [Toggle Api Key](https://docs.lyceum.technology/api-reference/api-keys/toggle-api-key.md): Toggle API key active status.
- [Validate Api Key](https://docs.lyceum.technology/api-reference/api-keys/validate-api-key.md): Validate an API key and return information about it.
- [Login](https://docs.lyceum.technology/api-reference/authentication/login.md): Login with email and password, return JWT tokens. This JWT can be used directly with MinIO STS.
- [Refresh Token](https://docs.lyceum.technology/api-reference/authentication/refresh-token.md): Refresh an access token using a refresh token.
- [Cancel Batch](https://docs.lyceum.technology/api-reference/batch-api/cancel-batch.md): Cancel a batch job (following OpenAI batch API pattern).
- [Create Batch](https://docs.lyceum.technology/api-reference/batch-api/create-batch.md): Create a batch inference job (following OpenAI batch API pattern).
- [Get Batch](https://docs.lyceum.technology/api-reference/batch-api/get-batch.md): Retrieve a batch job (following OpenAI batch API pattern).
- [Get File Content](https://docs.lyceum.technology/api-reference/batch-api/get-file-content.md): Retrieve file content (following OpenAI Files API pattern).
- [Get File Info](https://docs.lyceum.technology/api-reference/batch-api/get-file-info.md): Get file metadata (following OpenAI Files API pattern).
- [List Batches](https://docs.lyceum.technology/api-reference/batch-api/list-batches.md): List batch jobs (following OpenAI batch API pattern).
- [Upload Batch File](https://docs.lyceum.technology/api-reference/batch-api/upload-batch-file.md): Upload a file for batch processing (following OpenAI pattern).
- [Create Checkout Session](https://docs.lyceum.technology/api-reference/billing-credits/create-checkout-session.md): Create a Stripe checkout session for purchasing credits.
- [Get Billing Activities](https://docs.lyceum.technology/api-reference/billing-credits/get-billing-activities.md): Get combined billing activities (executions + credit purchases).
- [Get Execution History](https://docs.lyceum.technology/api-reference/billing-credits/get-execution-history.md): Get user's execution history.
- [Get Invoices](https://docs.lyceum.technology/api-reference/billing-credits/get-invoices.md): Get user's credit purchase invoices/receipts.
- [Get User Credits](https://docs.lyceum.technology/api-reference/billing-credits/get-user-credits.md): Get current user's credit balance.
- [Get User Credits Details](https://docs.lyceum.technology/api-reference/billing-credits/get-user-credits-details.md): Get detailed user credits information including Stripe data.
- [Create Dedicated Deployment](https://docs.lyceum.technology/api-reference/dedicated-deployment-external/create-dedicated-deployment.md)
- [Delete Dedicated Deployment](https://docs.lyceum.technology/api-reference/dedicated-deployment-external/delete-dedicated-deployment.md)
- [Get Dedicated Deployment](https://docs.lyceum.technology/api-reference/dedicated-deployment-external/get-dedicated-deployment.md): Get deployment details and all replicas.
- [List Dedicated Deployments](https://docs.lyceum.technology/api-reference/dedicated-deployment-external/list-dedicated-deployments.md): List dedicated deployments.
- [Abort Docker Compose Execution](https://docs.lyceum.technology/api-reference/docker-compose-execution/abort-docker-compose-execution.md): Abort a running Docker Compose execution.
- [Complete Docker Compose Execution](https://docs.lyceum.technology/api-reference/docker-compose-execution/complete-docker-compose-execution.md): Complete Docker Compose execution endpoint called after streaming finishes. Updates the Supabase record with final output and status.
- [Start Docker Compose Execution](https://docs.lyceum.technology/api-reference/docker-compose-execution/start-docker-compose-execution.md): Start Docker Compose execution and return direct streaming URL.
- [Abort Docker Execution](https://docs.lyceum.technology/api-reference/docker-execution/abort-docker-execution.md): Abort a running Docker execution.
- [Complete Docker Execution](https://docs.lyceum.technology/api-reference/docker-execution/complete-docker-execution.md): Complete Docker execution endpoint called after streaming finishes. Updates the Supabase record with final output and status.
- [Start Docker Execution](https://docs.lyceum.technology/api-reference/docker-execution/start-docker-execution.md): Start Docker container execution and return direct streaming URL.
- [Get Email Preferences](https://docs.lyceum.technology/api-reference/email-preferences/get-email-preferences.md): Get user's current email preferences.
- [Resubscribe To Emails](https://docs.lyceum.technology/api-reference/email-preferences/resubscribe-to-emails.md): Resubscribe to all email categories.
- [Unsubscribe From Emails](https://docs.lyceum.technology/api-reference/email-preferences/unsubscribe-from-emails.md): Unsubscribe from email categories. This endpoint does NOT require authentication (can be called from email links).
- [Update Email Preferences](https://docs.lyceum.technology/api-reference/email-preferences/update-email-preferences.md): Update user's email preferences.
- [Delete All Environment Variables](https://docs.lyceum.technology/api-reference/environment-variables/delete-all-environment-variables.md): Delete all environment variables for the user.
- [Delete Environment Variable](https://docs.lyceum.technology/api-reference/environment-variables/delete-environment-variable.md): Delete a single environment variable.
- [List Environment Variables](https://docs.lyceum.technology/api-reference/environment-variables/list-environment-variables.md): List all environment variables for the authenticated user.
- [Upsert Environment Variables](https://docs.lyceum.technology/api-reference/environment-variables/upsert-environment-variables.md): Create or update one or more environment variables.
- [Delete Execution](https://docs.lyceum.technology/api-reference/execution-management/delete-execution.md): Delete an execution record.
- [Get Execution](https://docs.lyceum.technology/api-reference/execution-management/get-execution.md): Get execution details.
- [Get Execution Timing](https://docs.lyceum.technology/api-reference/execution-management/get-execution-timing.md): Get execution timing details.
- [Get Gpu Selection Status](https://docs.lyceum.technology/api-reference/gpu-selection-execution/get-gpu-selection-status.md): Get the current status of a GPU selection execution.
- [Start Gpu Selection](https://docs.lyceum.technology/api-reference/gpu-selection-execution/start-gpu-selection.md): Start GPU selection execution.
- [Ping](https://docs.lyceum.technology/api-reference/health/ping.md): Health check endpoint for the Lyceum FastAPI Server.
- [Version](https://docs.lyceum.technology/api-reference/health/version.md): Get FastAPI and system version information.
- [Create Chat Completion](https://docs.lyceum.technology/api-reference/inference/create-chat-completion.md): OpenAI-compatible Chat Completion endpoint.
- [API Reference](https://docs.lyceum.technology/api-reference/introduction.md): REST API for Lyceum Cloud
- [Get Machine Types](https://docs.lyceum.technology/api-reference/machine-types/get-machine-types.md): Get all available machine types from the pricing table.
- [Disable Mfa](https://docs.lyceum.technology/api-reference/mfa/disable-mfa.md): Disable MFA for the user. Requires a valid TOTP code or backup code.
- [Enroll Mfa](https://docs.lyceum.technology/api-reference/mfa/enroll-mfa.md): Enroll user in MFA using TOTP (Time-based One-Time Password). Returns a secret key and QR code that can be scanned by authenticator apps.
- [Get Mfa Status](https://docs.lyceum.technology/api-reference/mfa/get-mfa-status.md): Get the current MFA status for the user.
- [Regenerate Backup Codes](https://docs.lyceum.technology/api-reference/mfa/regenerate-backup-codes.md): Regenerate backup codes. Requires a valid TOTP code for security. This invalidates all previous backup codes.
- [Verify Mfa Code](https://docs.lyceum.technology/api-reference/mfa/verify-mfa-code.md): Verify a TOTP code during login or for sensitive operations. Can also accept backup codes.
- [Verify Mfa Enrollment](https://docs.lyceum.technology/api-reference/mfa/verify-mfa-enrollment.md): Verify MFA enrollment by checking the TOTP code. This activates MFA for the user.
- [Get Execution Metrics](https://docs.lyceum.technology/api-reference/observability--gpu-metrics/get-execution-metrics.md): Get GPU and system metrics from Prometheus for a specific execution.
- [Get Execution Logs](https://docs.lyceum.technology/api-reference/observability--logs/get-execution-logs.md): Get all logs for a specific execution.
- [Get User Logs](https://docs.lyceum.technology/api-reference/observability--logs/get-user-logs.md): Get all logs for the current user.
- [Get Available Resources](https://docs.lyceum.technology/api-reference/resources/get-available-resources.md): List all available hardware resources including prices.
- [Get Storage Credentials](https://docs.lyceum.technology/api-reference/storage-credentials/get-storage-credentials.md): Generate temporary MinIO/S3 storage credentials using STS.
- [Delete File](https://docs.lyceum.technology/api-reference/storage-files/delete-file.md): Delete a file from user's S3 bucket.
- [Delete Folder](https://docs.lyceum.technology/api-reference/storage-files/delete-folder.md): Delete all files in a folder (by prefix).
- [Download File](https://docs.lyceum.technology/api-reference/storage-files/download-file.md): Download a file from user's S3 bucket.
- [List Files](https://docs.lyceum.technology/api-reference/storage-files/list-files.md): List files in user's S3 bucket.
- [Upload Bulk Files](https://docs.lyceum.technology/api-reference/storage-files/upload-bulk-files.md): Upload multiple files at once, optionally preserving folder structure.
- [Upload File](https://docs.lyceum.technology/api-reference/storage-files/upload-file.md): Upload a file to user's S3 bucket.
- [Abort Execution](https://docs.lyceum.technology/api-reference/streaming-execution/abort-execution.md): Abort a running execution.
- [Complete Execution](https://docs.lyceum.technology/api-reference/streaming-execution/complete-execution.md): Complete execution endpoint called by the extension after streaming finishes. Updates the Supabase record with final output and status.
- [Get Execution Status](https://docs.lyceum.technology/api-reference/streaming-execution/get-execution-status.md): Get the current status of an execution.
- [Start Streaming Execution](https://docs.lyceum.technology/api-reference/streaming-execution/start-streaming-execution.md): Start execution and return direct streaming URL.
- [Stream Inference](https://docs.lyceum.technology/api-reference/streaming-inference/stream-inference.md): Server-Sent Events endpoint for inference results. Emits 'queued' immediately, then 'finished' or 'failed'.
- [Delete User](https://docs.lyceum.technology/api-reference/user-management/delete-user.md): Delete the current authenticated user's account.
- [Get User Status](https://docs.lyceum.technology/api-reference/user-management/get-user-status.md): Check user's authentication status and profile information.
- [Get Available Hardware Profiles](https://docs.lyceum.technology/api-reference/user-quotas/get-available-hardware-profiles.md): Get list of hardware profiles available to the user based on their quotas and pricing table.
- [Get User Quotas](https://docs.lyceum.technology/api-reference/user-quotas/get-user-quotas.md): Get user's machine type quotas and permissions.
- [Create Vm](https://docs.lyceum.technology/api-reference/vm-management/create-vm.md): Create a new VM with specified hardware requirements. Requires sufficient credits and calls the VM provisioning service.
- [Get Vm Availability](https://docs.lyceum.technology/api-reference/vm-management/get-vm-availability.md): Get hardware profiles from the VM provisioning service which the user is allowed to provision. Availability does not automatically imply that the requested hardware is actually available right now.
- [Get Vm Status](https://docs.lyceum.technology/api-reference/vm-management/get-vm-status.md): Get detailed status of a specific VM from VM provisioning service.
- [List Vms](https://docs.lyceum.technology/api-reference/vm-management/list-vms.md): List VMs for the current user with optional status filtering.
- [Terminate Vm](https://docs.lyceum.technology/api-reference/vm-management/terminate-vm.md): Terminate and delete a VM permanently.
- [Redeem Voucher](https://docs.lyceum.technology/api-reference/voucher/redeem-voucher.md): Redeem a voucher and add credits to user's account.
- [Validate Voucher](https://docs.lyceum.technology/api-reference/voucher/validate-voucher.md): Validate a voucher code.
- [Abort Execution](https://docs.lyceum.technology/api-reference/workload-management/abort-execution.md): Abort a specific execution by setting cancel=true in the database.
- [List Non Complete Executions](https://docs.lyceum.technology/api-reference/workload-management/list-non-complete-executions.md): List all non-completed executions for the current user.
- [Stop Execution](https://docs.lyceum.technology/api-reference/workload-management/stop-execution.md): Gracefully stop a running execution and mark it as completed.
- [CLI Reference](https://docs.lyceum.technology/cli-reference/introduction.md): Complete reference for the lyceum command-line tool
- [Billing](https://docs.lyceum.technology/docs/account/billing.md): Credits, invoices, and execution history
- [Settings](https://docs.lyceum.technology/docs/account/settings.md): Profile, security, MFA, quotas, and account management
- [API Keys](https://docs.lyceum.technology/docs/configuration/api-keys.md): Authenticate the CLI, scripts, and integrations
- [Machine Types](https://docs.lyceum.technology/docs/configuration/machine-types.md): GPU and CPU options for serverless workloads and VM instances
- [Storage](https://docs.lyceum.technology/docs/configuration/storage.md): Per-user S3-compatible bucket
- [Lyceum Cloud](https://docs.lyceum.technology/docs/index.md): Run Python, Docker, notebooks, and dedicated inference on managed GPU infrastructure
- [Active Models](https://docs.lyceum.technology/docs/inference/active-models.md): Inspect running dedicated deployments and replica health
- [Dedicated Inference](https://docs.lyceum.technology/docs/inference/dedicated.md): Deploy a Hugging Face model to a dedicated GPU endpoint with autoscaling
- [Serverless Inference](https://docs.lyceum.technology/docs/inference/serverless.md): Pay-per-request inference endpoints
- [Streaming Inference](https://docs.lyceum.technology/docs/inference/streaming.md): Stream inference results over Server-Sent Events
- [Launch an Instance](https://docs.lyceum.technology/docs/instances/launch.md): Provision a dedicated GPU VM with SSH access
- [Your VMs](https://docs.lyceum.technology/docs/instances/vms.md): Manage long-lived GPU virtual machines
- [Logs](https://docs.lyceum.technology/docs/observability/logs.md): Query stdout, stderr, and platform logs from your runs
- [GPU & System Metrics](https://docs.lyceum.technology/docs/observability/metrics.md): Query per-execution GPU and system metrics from Prometheus
- [Dashboard Overview](https://docs.lyceum.technology/docs/overview.md): Navigate the Lyceum Cloud dashboard
- [Quickstart](https://docs.lyceum.technology/docs/quickstart.md): Create an account, install the CLI or VS Code extension, and run your first job
- [Webhook Callbacks](https://docs.lyceum.technology/docs/serverless/callbacks.md): Get notified when a run finishes by having Lyceum POST to your URL
- [Launch a Run](https://docs.lyceum.technology/docs/serverless/launch-run.md): Submit Python, Docker, or Docker Compose workloads
- [Runs](https://docs.lyceum.technology/docs/serverless/runs.md): Monitor and manage executions on Lyceum Cloud
- [Secrets](https://docs.lyceum.technology/docs/serverless/secrets.md): Store environment variables and credentials for your runs
- [Pythia](https://docs.lyceum.technology/docs/tools/pythia.md): Automatically find the right GPU for your PyTorch workload
- [Clusters](https://docs.lyceum.technology/docs/workloads/clusters.md): Dedicated multi-node GPU clusters with InfiniBand networking
- [Docker Execution](https://docs.lyceum.technology/docs/workloads/docker-execution.md): Run any OCI-compatible Docker container on Lyceum Cloud, with optional GPU
- [Notebooks](https://docs.lyceum.technology/docs/workloads/notebooks.md): Launch Jupyter notebook servers on Lyceum Cloud machines
- [Python Execution](https://docs.lyceum.technology/docs/workloads/python-execution.md): Run Python code and Jupyter notebooks on Lyceum Cloud from VS Code or the CLI
- [End-to-End API Workflow](https://docs.lyceum.technology/examples/api-integration.md): Authenticate, list machines, submit a run, and stream the result over the REST API
- [Upload and Process Data](https://docs.lyceum.technology/examples/data-processing.md): Move files into your storage bucket and read them from a run
- [Run Docker Containers](https://docs.lyceum.technology/examples/docker-containers.md): Submit Docker images and Docker Compose stacks to Lyceum Cloud
- [Deploy a Hugging Face Model](https://docs.lyceum.technology/examples/machine-learning.md): Stand up a dedicated inference endpoint and call it like OpenAI
- [Run Python](https://docs.lyceum.technology/examples/python-basics.md): Submit Python code to Lyceum Cloud from the CLI or REST API
- [VM Instances](https://docs.lyceum.technology/examples/vm-instances.md): Provision GPU/CPU virtual machines and run workloads on them

## OpenAPI Specs

- [openapi](https://docs.lyceum.technology/api-reference/openapi.json)