# Cerebrium

> Cerebrium developer documentation for real-time and production AI workloads. Learn how to deploy low-latency inference APIs, voice agents, multi-region apps, serverless GPUs and CPUs, and workloads that need strong cold-start and scaling performance.

## Docs

- [Create API Key](https://cerebrium.ai/docs/api-reference/api-keys/create-api-key.md): Create a new API key for a project.
- [List API Keys](https://cerebrium.ai/docs/api-reference/api-keys/list-api-keys.md): List all API keys for a project.
- [Create App](https://cerebrium.ai/docs/api-reference/apps/create-app.md): Create a new app for a specific project using manual upload.
- [Create GitHub App](https://cerebrium.ai/docs/api-reference/apps/create-github-app.md): Create a new app linked to a GitHub repository for automatic deployments.
- [Create Partner App](https://cerebrium.ai/docs/api-reference/apps/create-partner-app.md): Create a new app from a partner template.
- [Create Run App](https://cerebrium.ai/docs/api-reference/apps/create-run-app.md): Create an app if it does not already exist, used by the CLI before running code.
- [Delete App](https://cerebrium.ai/docs/api-reference/apps/delete-app.md): Remove a specific app from a project.
- [Get Active Revision](https://cerebrium.ai/docs/api-reference/apps/get-active-revision.md): Retrieve the active revision for a specific app.
- [Get App](https://cerebrium.ai/docs/api-reference/apps/get-app.md): Retrieve details for a specific app in a project.
- [Get App Cost](https://cerebrium.ai/docs/api-reference/apps/get-app-cost.md): Retrieve cost breakdown for a specific app.
- [Get App Logs](https://cerebrium.ai/docs/api-reference/apps/get-app-logs.md): Retrieve logs for a specific app.
- [Get App Resource Metrics](https://cerebrium.ai/docs/api-reference/apps/get-app-resource-metrics.md): Retrieve CPU, memory, and GPU utilization metrics for an app over a time period.
- [Get Dashboard Metrics](https://cerebrium.ai/docs/api-reference/apps/get-dashboard-metrics.md): Retrieve summary metrics for an app's dashboard view.
- [List Apps](https://cerebrium.ai/docs/api-reference/apps/list-apps.md): Retrieve a list of apps for a specific project.
- [Modify App](https://cerebrium.ai/docs/api-reference/apps/modify-app.md): Update the configuration or metadata of a specific app.
- [Apply Coupon](https://cerebrium.ai/docs/api-reference/billing/apply-coupon.md): Apply a promotional coupon code to the project's billing account.
- [Get Billing Graph](https://cerebrium.ai/docs/api-reference/billing/get-billing-graph.md): Retrieve daily billing cost data per app as time series for charting.
- [Cancel Build](https://cerebrium.ai/docs/api-reference/builds/cancel-build.md): Cancel an ongoing build for an app.
- [Create Base Image Hash](https://cerebrium.ai/docs/api-reference/builds/create-base-image-hash.md): Generate a SHA256 hash from dependency lists to determine if a base image rebuild is needed.
- [Download Build](https://cerebrium.ai/docs/api-reference/builds/download-build.md): Download the build ZIP file for a specific build.
- [Get Build](https://cerebrium.ai/docs/api-reference/builds/get-build.md): Retrieve details for a specific build.
- [Get Build Zip Contents](https://cerebrium.ai/docs/api-reference/builds/get-build-zip-contents.md): List the files contained in a build's uploaded ZIP archive.
- [Health Check](https://cerebrium.ai/docs/api-reference/builds/health-check.md): Check if the build service is operational.
- [List Build Logs](https://cerebrium.ai/docs/api-reference/builds/list-build-logs.md): Retrieve logs for a specific build of an app.
- [List Builds](https://cerebrium.ai/docs/api-reference/builds/list-builds.md): Retrieve a list of builds for a specific app.
- [List Image Files](https://cerebrium.ai/docs/api-reference/builds/list-image-files.md): Browse files inside a built container image at a specified path.
- [Rebuild](https://cerebrium.ai/docs/api-reference/builds/rebuild.md): Trigger a new build using the same source as an existing build.
- [Run App](https://cerebrium.ai/docs/api-reference/cerebrium-run/run-app.md): Execute code on a deployed app.
- [Get Container](https://cerebrium.ai/docs/api-reference/containers/get-container.md): Retrieve details for a specific container.
- [Get Container Events](https://cerebrium.ai/docs/api-reference/containers/get-container-events.md): Retrieve lifecycle events for a container such as eviction, OOM, and spot interruption.
- [Get Queue Depth](https://cerebrium.ai/docs/api-reference/containers/get-queue-depth.md): Get real-time queue depth counts (proxyQueued, containerQueued, processing) from ClickHouse
- [List Active Containers](https://cerebrium.ai/docs/api-reference/containers/list-active-containers.md): Retrieve all active containers, including those in terminating state.
- [List Container Readiness](https://cerebrium.ai/docs/api-reference/containers/list-container-readiness.md): Retrieve the ready/not-ready status of each container.
- [List Container Resource Usage](https://cerebrium.ai/docs/api-reference/containers/list-container-resource-usage.md): Retrieve current CPU and memory usage per container with totals.
- [List Containers](https://cerebrium.ai/docs/api-reference/containers/list-containers.md): Retrieve a list of containers for a specific app.
- [List Containers (7 Days)](https://cerebrium.ai/docs/api-reference/containers/list-containers-7-days.md): Retrieve containers for an app from the last 7 days.
- [List Recent Containers](https://cerebrium.ai/docs/api-reference/containers/list-recent-containers.md): Retrieve a list of recent containers for a specific app.
- [List Recent Containers](https://cerebrium.ai/docs/api-reference/containers/list-recent-containers-1.md): Retrieve recently active containers across all apps in a project.
- [Search Containers](https://cerebrium.ai/docs/api-reference/containers/search-containers.md): Search containers by ID or status with pagination.
- [Stop Container](https://cerebrium.ai/docs/api-reference/containers/stop-container.md): Stop a specific container.
- [Assign Domain to App](https://cerebrium.ai/docs/api-reference/custom-domains/assign-domain-to-app.md): Assign a validated custom domain to a specific app.
- [Create Custom Domain](https://cerebrium.ai/docs/api-reference/custom-domains/create-custom-domain.md): Create a new custom domain for a project with DNS validation records.
- [Delete Custom Domain](https://cerebrium.ai/docs/api-reference/custom-domains/delete-custom-domain.md): Remove a custom domain from a project. Domain must be unassigned from all apps first.
- [Get Custom Domain](https://cerebrium.ai/docs/api-reference/custom-domains/get-custom-domain.md): Retrieve details for a specific custom domain.
- [List Custom Domains](https://cerebrium.ai/docs/api-reference/custom-domains/list-custom-domains.md): Retrieve a list of custom domains for a specific project.
- [Unassign Domain from App](https://cerebrium.ai/docs/api-reference/custom-domains/unassign-domain-from-app.md): Remove the assignment between a domain and an app.
- [Validate Custom Domain](https://cerebrium.ai/docs/api-reference/custom-domains/validate-custom-domain.md): Manually trigger DNS validation for a custom domain. Useful for retrying failed validations after DNS configuration changes.
- [Complete File Upload](https://cerebrium.ai/docs/api-reference/files/complete-file-upload.md): Finalize the file upload process to a specific volume. Intended for internal use - rather use the `cerebrium cp` command.
- [Delete File](https://cerebrium.ai/docs/api-reference/files/delete-file.md): Remove a file from a specific volume. Intended for internal use - rather use the `cerebrium rm` command.
- [Download File](https://cerebrium.ai/docs/api-reference/files/download-file.md): Download a file from a specific volume.
- [Initialize File Upload](https://cerebrium.ai/docs/api-reference/files/initialize-file-upload.md): Begin the file upload process to a specific volume. Intended for internal use - rather use the `cerebrium cp` command.
- [List Files](https://cerebrium.ai/docs/api-reference/files/list-files.md): Retrieve a list of files in a specified volume. Intended for internal use - rather use the `cerebrium ls` command.
- [List Hardware](https://cerebrium.ai/docs/api-reference/hardware/list-hardware.md): Retrieve available hardware types and their specifications.
- [Get GitHub Install URL](https://cerebrium.ai/docs/api-reference/integrations/get-github-install-url.md): Generate a GitHub App installation URL for a project.
- [Get Repo File Tree](https://cerebrium.ai/docs/api-reference/integrations/get-repo-file-tree.md): Retrieve the file tree for a GitHub repository.
- [Get Repo Metadata](https://cerebrium.ai/docs/api-reference/integrations/get-repo-metadata.md): Retrieve metadata for a GitHub repository.
- [Get TOML Config](https://cerebrium.ai/docs/api-reference/integrations/get-toml-config.md): Parse and retrieve the cerebrium.toml configuration from a GitHub repository.
- [List GitHub Branches](https://cerebrium.ai/docs/api-reference/integrations/list-github-branches.md): List branches for a GitHub repository.
- [List GitHub Repos](https://cerebrium.ai/docs/api-reference/integrations/list-github-repos.md): List accessible GitHub repositories for the project's GitHub integration.
- [List Integrations](https://cerebrium.ai/docs/api-reference/integrations/list-integrations.md): List all integrations for a project.
- [Remove GitHub Integration](https://cerebrium.ai/docs/api-reference/integrations/remove-github-integration.md): Remove the GitHub integration from a project.
- [Get Execution Time Metrics](https://cerebrium.ai/docs/api-reference/metrics/get-execution-time-metrics.md): Retrieve run execution time percentiles for an app.
- [Get Response Time Metrics](https://cerebrium.ai/docs/api-reference/metrics/get-response-time-metrics.md): Retrieve end-to-end response time percentiles for an app.
- [Get Startup Time Metrics](https://cerebrium.ai/docs/api-reference/metrics/get-startup-time-metrics.md): Retrieve cold start and container startup time metrics for an app.
- [List Notifications](https://cerebrium.ai/docs/api-reference/notifications/list-notifications.md): Retrieve active notifications and announcements.
- [List Plans](https://cerebrium.ai/docs/api-reference/plans/list-plans.md): Retrieve available subscription plans and their features.
- [Create Project](https://cerebrium.ai/docs/api-reference/projects/create-project.md): Create a new project.
- [Delete Project](https://cerebrium.ai/docs/api-reference/projects/delete-project.md): Remove a specific project.
- [Get Project](https://cerebrium.ai/docs/api-reference/projects/get-project.md): Retrieve details of a specific project by its ID.
- [Get Project Cost](https://cerebrium.ai/docs/api-reference/projects/get-project-cost.md): Retrieve current billing period cost breakdown for a project.
- [List Projects](https://cerebrium.ai/docs/api-reference/projects/list-projects.md): Retrieve a list of projects.
- [Modify Project](https://cerebrium.ai/docs/api-reference/projects/modify-project.md): Update the configuration or metadata of a specific project.
- [Cancel Run](https://cerebrium.ai/docs/api-reference/runs/cancel-run.md): Cancel an ongoing run for an app.
- [Count Queued Runs](https://cerebrium.ai/docs/api-reference/runs/count-queued-runs.md): Retrieve the number of queued runs for a specific app.
- [Get Run](https://cerebrium.ai/docs/api-reference/runs/get-run.md): Retrieve details for a specific run of an app.
- [Get Runs Chart Data](https://cerebrium.ai/docs/api-reference/runs/get-runs-chart-data.md): Retrieve aggregated run data optimized for charting over long time ranges.
- [List Runs](https://cerebrium.ai/docs/api-reference/runs/list-runs.md): Retrieve a list of runs for a specific app.
- [List App Secrets](https://cerebrium.ai/docs/api-reference/secrets/list-app-secrets.md): Retrieve a list of secrets for a specific app.
- [List Secrets](https://cerebrium.ai/docs/api-reference/secrets/list-secrets.md): Retrieve a list of secrets for a specific project.
- [Update App Secrets](https://cerebrium.ai/docs/api-reference/secrets/update-app-secrets.md): Modify secrets for a specific app.
- [Update Secrets](https://cerebrium.ai/docs/api-reference/secrets/update-secrets.md): Modify secrets for a specific project.
- [Create Service Account](https://cerebrium.ai/docs/api-reference/service-accounts/create-service-account.md): Create a new service account for a project.
- [Delete Service Account](https://cerebrium.ai/docs/api-reference/service-accounts/delete-service-account.md): Delete a service account.
- [List Service Account Keys](https://cerebrium.ai/docs/api-reference/service-accounts/list-service-account-keys.md): List all tokens for a service account.
- [List Service Accounts](https://cerebrium.ai/docs/api-reference/service-accounts/list-service-accounts.md): List all service accounts for a project.
- [Update Service Account](https://cerebrium.ai/docs/api-reference/service-accounts/update-service-account.md): Update service account grants.
- [Get Metrics Export Config](https://cerebrium.ai/docs/api-reference/settings/get-metrics-export-config.md): Retrieve the OTLP metrics export configuration for a project.
- [Test Metrics Export](https://cerebrium.ai/docs/api-reference/settings/test-metrics-export.md): Send a test metric to validate the configured OTLP endpoint.
- [Update Metrics Export Config](https://cerebrium.ai/docs/api-reference/settings/update-metrics-export-config.md): Update the OTLP metrics export configuration. Supports partial updates.
- [Change Plan](https://cerebrium.ai/docs/api-reference/subscriptions/change-plan.md): Upgrade or downgrade the subscription plan for a project.
- [Get Payment URL](https://cerebrium.ai/docs/api-reference/subscriptions/get-payment-url.md): Generate a Stripe checkout URL for adding a payment method.
- [Get Subscription](https://cerebrium.ai/docs/api-reference/subscriptions/get-subscription.md): Retrieve the current subscription plan and status for a project.
- [List Invoices](https://cerebrium.ai/docs/api-reference/subscriptions/list-invoices.md): Retrieve billing invoices for a project.
- [List Payment Methods](https://cerebrium.ai/docs/api-reference/subscriptions/list-payment-methods.md): Retrieve saved payment methods for a project.
- [Remove Payment Method](https://cerebrium.ai/docs/api-reference/subscriptions/remove-payment-method.md): Delete a saved payment method from a project.
- [Invite User](https://cerebrium.ai/docs/api-reference/users/invite-user.md): Invite a user to join a project.
- [List Invitations](https://cerebrium.ai/docs/api-reference/users/list-invitations.md): Retrieve pending project invitations for the authenticated user.
- [List Users](https://cerebrium.ai/docs/api-reference/users/list-users.md): Retrieve all users with access to a project.
- [Remove User](https://cerebrium.ai/docs/api-reference/users/remove-user.md): Remove a user from a project.
- [Respond to Invitation](https://cerebrium.ai/docs/api-reference/users/respond-to-invitation.md): Accept or reject an invitation to join a project.
- [List Volumes](https://cerebrium.ai/docs/api-reference/volumes/list-volumes.md): Retrieve a list of volumes for a specific project.
- [Resize Volume](https://cerebrium.ai/docs/api-reference/volumes/resize-volume.md): Modify the size of a specific volume.
- [Calculating compute cost](https://cerebrium.ai/docs/calculating-cost.md): How to calculate the cost of your deployment on Cerebrium
- [Custom Dockerfiles](https://cerebrium.ai/docs/container-images/custom-dockerfiles.md): Run generic containerized applications on Cerebrium using your own custom Dockerfiles.
- [Custom Python Web Servers](https://cerebrium.ai/docs/container-images/custom-web-servers.md): Run ASGI/WSGI Python apps on Cerebrium
- [Defining Container Images](https://cerebrium.ai/docs/container-images/defining-container-images.md)
- [Using Private Docker Registries](https://cerebrium.ai/docs/container-images/private-docker-registry.md): How to authenticate, pull, and use private Docker images as base images in your deployments.
- [CI/CD Pipelines](https://cerebrium.ai/docs/deployments/ci-cd.md): Automate Cerebrium deployments using GitHub Actions
- [Gradual Roll-out](https://cerebrium.ai/docs/deployments/gradual-roll-out.md): Control the transition between revisions during deployments
- [Multi-Region Deployment](https://cerebrium.ai/docs/deployments/multi-region-deployment.md): Deploy your apps globally across multiple regions for improved latency and data residency compliance
- [Async requests](https://cerebrium.ai/docs/endpoints/async.md): Execute calls to a Cerebrium app to be run asynchronously
- [REST API](https://cerebrium.ai/docs/endpoints/inference-api.md): Make authenticated HTTP requests to your Cerebrium endpoints
- [OpenAI-Compatible Endpoints](https://cerebrium.ai/docs/endpoints/openai-compatible-endpoints.md)
- [Streaming Endpoints](https://cerebrium.ai/docs/endpoints/streaming.md)
- [Webhook Forwarding](https://cerebrium.ai/docs/endpoints/webhook.md): Forward responses to a specified webhook
- [WebSocket Endpoints](https://cerebrium.ai/docs/endpoints/websockets.md)
- [Introduction](https://cerebrium.ai/docs/getting-started/introduction.md): Start with Cerebrium when latency, burst traffic, and production AI constraints matter from day one.
- [CPU and Memory](https://cerebrium.ai/docs/hardware/cpu-and-memory.md)
- [Using CUDA](https://cerebrium.ai/docs/hardware/using-cuda.md)
- [Using GPUs](https://cerebrium.ai/docs/hardware/using-gpus.md)
- [Exporting Metrics to Monitoring Platforms](https://cerebrium.ai/docs/integrations/metrics-export.md): Export your application metrics to any OTLP-compatible observability platform including Grafana Cloud, Datadog, Prometheus, New Relic, and more
- [Migrating from Hugging Face](https://cerebrium.ai/docs/migrations/hugging-face.md): Deploy a Model from Hugging Face on Cerebrium
- [Migrating from Mystic](https://cerebrium.ai/docs/migrations/mystic.md): Deploy a Model from Mystic on Cerebrium
- [Migrating from Replicate](https://cerebrium.ai/docs/migrations/replicate.md): Deploy a Model from Replicate on Cerebrium
- [Custom Domains](https://cerebrium.ai/docs/networking/custom-domains.md): Connect your own domain to your Cerebrium project
- [Inter-cluster routing](https://cerebrium.ai/docs/networking/inter-cluster-routing.md): Route to your apps privately in cluster with minimal latency
- [Faster Cold Starts](https://cerebrium.ai/docs/other-topics/faster-cold-starts.md): Decrease the time it takes start your application
- [Request and Response Logging](https://cerebrium.ai/docs/other-topics/request-response-logging.md): Control request and response logs in your Cerebrium apps
- [Using Secrets](https://cerebrium.ai/docs/other-topics/using-secrets.md): Access third-party platforms using secure credentials encrypted on Cerebrium
- [Deepgram](https://cerebrium.ai/docs/partner-services/deepgram.md): Deploy Deepgram speech-to-text services on Cerebrium
- [Introduction](https://cerebrium.ai/docs/partner-services/index.md): Deploy specialized services from Cerebrium's partners with simplified configurations
- [Rime](https://cerebrium.ai/docs/partner-services/rime.md): Deploy Rime text-to-speech services on Cerebrium
- [Batching and Concurrency](https://cerebrium.ai/docs/scaling/batching-concurrency.md): Improve throughput and cost performance with batching and concurrency
- [Preemption and Graceful Termination](https://cerebrium.ai/docs/scaling/graceful-termination.md): Implementing Graceful Termination of Instances by Handling Termination Signals
- [Scaling Apps](https://cerebrium.ai/docs/scaling/scaling-apps.md): Learn to optimise for cost and performance by scaling out apps
- [Security & Data Privacy](https://cerebrium.ai/docs/security.md): Cerebrium follows security best practices
- [Managing Files](https://cerebrium.ai/docs/storage/managing-files.md)
- [TOML Reference](https://cerebrium.ai/docs/toml-reference/toml-reference.md): Complete reference for all parameters available in Cerebrium's default `cerebrium.toml` configuration file.
- [Gradio Chat Interface](https://cerebrium.ai/docs/v4/examples/asgi-gradio-interface.md): Using FastAPI, Gradio and Cerebrium to deploy an LLM chat interface
- [ComfyUI application at Scale](https://cerebrium.ai/docs/v4/examples/comfyUI.md): Deploy a ComfyUI application
- [Deploy a Vision Language Model with SGLang](https://cerebrium.ai/docs/v4/examples/deploy-a-vision-language-model-with-sglang.md): Build an intelligent ad analysis system that evaluates advertisements across multiple dimensions
- [Deploy Triton Inference server and TensorRT-LLM](https://cerebrium.ai/docs/v4/examples/deploy-an-llm-with-tensorrtllm-tritonserver.md): Achieve high throughput with Triton Inference Server and the TensorRT-LLM framework
- [Featured Examples](https://cerebrium.ai/docs/v4/examples/featured.md): Explore our collection of implementation examples and tutorials
- [Serving GPT-OSS with vLLM](https://cerebrium.ai/docs/v4/examples/gpt-oss.md): Deploy OpenAI's Latest Open Source Model
- [Deploy a High Throughput Server for Embeddings and Reranking](https://cerebrium.ai/docs/v4/examples/high-throughput-embeddings.md): Deploy a a high-throughput, low-latency REST API for serving text-embeddings, reranking models, clip, clap and colpali
- [Langchain and Langsmith](https://cerebrium.ai/docs/v4/examples/langchain-langsmith.md): Deploy an executive assistant using Langsmith and Langchain
- [Outbound Agent with LiveKit](https://cerebrium.ai/docs/v4/examples/livekit-outbound-agent.md): Create an Outbound AI agent that can transfer calls to real agents
- [OpenAI compatible vLLM endpoint](https://cerebrium.ai/docs/v4/examples/openai-compatible-endpoint-vllm.md): Create a OpenAI compatible endpoint using the vLLM framework
- [Real-time Voice Agent](https://cerebrium.ai/docs/v4/examples/realtime-voice-agents.md): Deploy a real-time AI voice agent
- [Generate Images using SDXL](https://cerebrium.ai/docs/v4/examples/sdxl.md): Generate high quality images using SDXL with refiner
- [Transcribe 1 hour podcast](https://cerebrium.ai/docs/v4/examples/transcribe-whisper.md): Using Distill Whisper to transcribe an audio file
- [Twilio Voice Agent with PipeCat](https://cerebrium.ai/docs/v4/examples/twilio-voice-agent.md): Integrate a real-time AI voice agent with Twilio
- [Hyperparameter Sweep training Llama 3.2 with WandB](https://cerebrium.ai/docs/v4/examples/wandb-sweep.md): Run a hyperparameter sweep on Llama 3.2 with WandB

## OpenAPI Specs

- [openapi_spec](https://s3.eu-west-1.amazonaws.com/www.cerebrium.ai/openapi_spec.json)
- [package](https://cerebrium.ai/docs/package.json)
- [training-dataset-example](https://cerebrium.ai/docs/data/training-dataset-example.json)

## Optional

- [Dashboard](https://dashboard.cerebrium.ai/login)
- [Blog](https://cerebrium.ai/blog)
- [Community](https://discord.gg/ATj6USmeE2)
- [Status](https://status.cerebrium.ai)
- [Pricing](https://www.cerebrium.ai/pricing)