A personal AI gateway with provider key management, automatic model fallback, an OpenAI-compatible API, and a web dashboard.
Launch in your Sealos workspace.
Start with the resources defined by the FreeLLMAPI template. Review CPU, memory, persistent storage, and network allocations for every service in Canvas. Capacity needs depend on your data and workload; monitor usage as they grow.
Template configuration and setupUse the application URL or connection details shown in Canvas. Follow the deployment guide for first-time account setup or client configuration, and keep generated credentials available for that step.
Sealos monthly plans include compute, memory, storage, and traffic. Size your plan for all deployed services. Software licenses and external AI or API services may have separate terms and charges. Confirm the applicable plan and optional charges in Cost Center.
Compare Sealos resource plansFor current cloud charges, refer to Sealos plan pricing. Upstream documentation may reference earlier billing models.
FreeLLMAPI is a personal AI gateway that manages provider credentials and routes requests through an OpenAI-compatible API. This template deploys the official FreeLLMAPI v0.9.8 image with its web dashboard and persistent SQLite storage on Sealos Cloud.
FreeLLMAPI combines provider key management, model routing, fallback chains, a chat playground, and request analytics. Add your own provider credentials after creating your dashboard account, then connect compatible clients using the gateway's unified API key and /v1 base URL. Provider availability, quotas, and charges follow each provider's terms.
The official container serves the React dashboard and Express API together on port 3001. Sealos provisions one application replica, a 1 GiB persistent volume, and a public HTTPS address. The SQLite database, saved conversations, provider settings, and encryption key survive Pod restarts on that volume.
This deployment follows FreeLLMAPI's personal, single-user model. The first account claims the dashboard; its password protects dashboard access, and the separate unified API key authenticates inference clients.
The template includes Node.js, the built dashboard, the API server, SQLite, and persistent storage. Provider credentials are configured inside FreeLLMAPI after deployment.
Architecture Components:
ghcr.io/tashfeenahmed/freellmapi:v0.9.8, serving the dashboard and API./app/server/data; runtime state lives in its runtime subdirectory.Configuration:
| Item | Template setting |
|---|---|
| Application replicas | 1 |
| Main container limits / requests | 100m CPU, 128Mi memory / 10m CPU, 12Mi memory |
| Initialization limits / requests | 100m CPU, 128Mi memory / 10m CPU, 12Mi memory |
| Database | /app/server/data/runtime/freeapi.db |
| Encryption key | /app/server/data/runtime/.encryption-key, owner-only 0600 permissions |
| Health endpoint | /api/ping |
| Runtime identity | Non-root UID/GID 1000 |
The encryption key is generated once from operating-system randomness, validated as 64 hexadecimal characters, and loaded as ENCRYPTION_KEY in production mode. Back up the database and its original encryption key together using a protected backup location. Keep one replica for this SQLite deployment and adjust CPU or memory as usage grows.
Private-network provider URLs are blocked with FREEAPI_BLOCK_PRIVATE_PROVIDER_URLS=true. Configure a publicly reachable HTTPS provider endpoint for custom providers.
License Information: FreeLLMAPI is licensed under the MIT License.
Sealos is built on Kubernetes and provides application management through Canvas, resource cards, and an AI dialog.
First-run setup code: line, enter that code in the form, and submit again. The code changes when an unclaimed server restarts and is consumed after registration.After registration, use the same email and password on Sign in. Account creation is available only until the first account has been created.
For password recovery, choose Forgot password? → Send reset code. Read the newly generated password reset code in the application's main container logs through Canvas, enter it with a new password of at least 8 characters, then sign in again. Log access is required for both remote first-run setup and password recovery.
Manage providers, models, routing, and client credentials inside FreeLLMAPI. For infrastructure changes, open Canvas and describe the change in the AI dialog or edit the application resource card. Increase CPU or memory for larger payloads or heavier concurrent use while retaining the single application replica.
The setup code is rejected: Read the latest First-run setup code: from the currently running main container. Restarting an unclaimed instance generates a fresh code.
A client receives an authentication error: Use the unified API key from Keys → Unified API key with this gateway. Configure the upstream provider's own key separately in Keys.
A model request fails: Check the provider's key, model ID, quota, and HTTPS base URL. A custom provider's model ID must match one that endpoint serves.
An existing database fails to start after its key was removed: Restore its original .encryption-key alongside the database. The initialization guard requires that original key to preserve access to encrypted provider credentials.
This Sealos template is provided under the template repository's license. FreeLLMAPI itself is distributed under the MIT License.
A shorter path from an app you want to an app you can run. Sealos brings deployment and ongoing operations into one place.
Start with a ready-made template. Review its configuration and launch from the Sealos console.
Run on managed infrastructure with built-in workload scheduling and recovery.
Give your application a public HTTPS endpoint with certificates managed for you.
Keep application data on persistent volumes across container restarts.
Adjust CPU, memory, and replicas from the console as your workload changes.
Sealos provisions the resources defined by your template and brings them together in your workspace.
Container workloads with configurable CPU, memory, and replicas.
An address for your app, with managed TLS certificates.
A database provisioned alongside your app when the template calls for one.
Storage for the files and data your application needs to keep.
Application settings and secrets configured in one place.
Inspect container logs and resource usage from the console.
Resources and their configuration vary by template. Review the deployment form for this app’s exact setup.
Explore more production-ready templates.
Build production-ready ai templates with Sealos.
Open Design is a local-first, open-source AI design workspace for generating prototypes, decks, images, videos, and design-system-driven artifacts.
Build production-ready ai templates with Sealos.
Host OpenClaw's AI agent gateway on Sealos with a browser control panel, token authentication, and persistent storage for configuration and workspaces.
Build production-ready ai templates with Sealos.
Host n8n workflow automation on Sealos with persistent storage and HTTPS webhooks. Choose PostgreSQL and Redis-backed queue mode as your workflows grow.