Back to templates
chatgpt-next-web icon

Deploy chatgpt-next-web on Sealos

NextChat is a light, fast AI assistant UI with GPT, Claude, DeepSeek, and Gemini support.

AI
Launch a private chatgpt-next-web AI workspace with one-click deployment.Keep models, prompts, and workflow data in your own Sealos environment.Scale GPU or CPU resources as your AI workload grows.Use an open-source template without managing Kubernetes YAML.
Official WebsiteGitHubREADME

Why deploy on Sealos

Sealos makes deploying any app effortless, secure, and production-ready. From one-click launch to ongoing operations, we handle the heavy lifting so you can focus on what matters.

One-Click Deploy
Sealos logo
Compute
Networking
Storage
Security
Observability
Your Application is Live

One-Click Deployment

Deploy any app template in seconds. No compose setup, manual configure, and go live.

Managed Kubernetes Reliability

Built on Sealos Managed Kubernetes for high availability, auto-scaling, and self-healing by default.

Automatic HTTPS & Security

Every deployment includes a secure domain with automatic SSL. We handle certificates and text protection for you.

Persistent Storage

Attach persistent volumes with ease. Your data stays safe, durable, and always accessible.

Scale when needed

Adjust resources as your app grows, no downtime required.

You Get the Whole Stack

Sealos provisions and connects every resource your application needs. Everything is ready to use.

One-click, fully provisionedSecure by defaultProduction ready

App Service

Your application is running and ready to serve requests.

Public HTTPS URL

Secure, global endpoint to access your application.

Database

Managed database instance for your application.

Persistent Volume

Durable storage for uploads and application data.

Environment Variables

Configuration and secrets injected securely into your app.

Logs & Metrics

Centralized logs and basic metrics are enabled.

README

README.md

Deploy and Host NextChat on Sealos

NextChat is a lightweight AI assistant web UI for OpenAI-compatible providers, Azure OpenAI, Claude, DeepSeek, Gemini, and other model gateways. This template deploys the official NextChat container with HTTPS access on Sealos Cloud.

NextChat Screenshot

About Hosting NextChat

NextChat runs as a single web application and stores chat state in the browser. The Sealos template creates a Deployment, Service, Ingress, and App entry, then injects model-provider settings through deployment inputs.

Access control is handled by the required CODE input. The template generates a unique default code, and users enter one of the comma-separated access codes on the first screen.

Common Use Cases

  • Private ChatGPT UI: Run a fast personal chat interface with your own API key.
  • Team Access Code Gateway: Share one HTTPS endpoint protected by one or more access codes.
  • OpenAI-Compatible Proxy UI: Point BASE_URL to a compatible gateway or self-hosted endpoint.
  • Azure OpenAI Frontend: Configure Azure deployment URL, key, and API version during deployment.

Deployment Guide

  1. Open the NextChat template and click Deploy Now.
  2. Enter OPENAI_API_KEY. Use commas to rotate multiple keys.
  3. Keep the generated CODE or replace it with a private comma-separated access password list.
  4. Optionally configure:
    • BASE_URL: OpenAI-compatible API base URL
    • HIDE_USER_API_KEY: set to 1 to hide the user API key field
    • DISABLE_GPT4: set to 1 to hide GPT-4 model choices
    • ENABLE_BALANCE_QUERY: set to 1 to enable balance query features
    • AZURE_URL, AZURE_API_KEY, AZURE_API_VERSION: Azure OpenAI settings
  5. Wait for the Deployment to become ready, then open the generated HTTPS URL from Sealos Canvas.
  6. Enter a value from CODE on the access-code screen.

Configuration

NameDescriptionRequiredDefault
OPENAI_API_KEYOpenAI-compatible API keys, comma-separated when multiple keys should be rotated.true<redacted>
CODEAccess codes for the web UI, comma-separated when multiple codes are allowed.truegenerated 16-character value
BASE_URLOpenAI-compatible API base URL for proxies or self-hosted endpoints.falsehttps://api.openai.com
OPENAI_ORG_IDOpenAI organization ID.false``
HIDE_USER_API_KEYSet to 1 to hide the user-provided API key field in the UI.false``
DISABLE_GPT4Set to 1 to disable GPT-4 model options.false``
ENABLE_BALANCE_QUERYSet to 1 to enable balance query features.false``
AZURE_URLAzure OpenAI deployment URL.falsehttps://{azure-resource-url}/openai/deployments/{deploy-name}
AZURE_API_KEYAzure OpenAI API key.false<redacted>
AZURE_API_VERSIONAzure OpenAI API version.false``

Store private API keys and access codes in Sealos-managed inputs. Keep CODE private because the public HTTPS endpoint uses the deployment's server-side model API key.

Scaling

The template is tuned for a small single-instance web UI. Increase CPU and memory from Sealos Canvas if many users share the same deployment or if the UI serves through a slower model gateway.

Troubleshooting

Access code is rejected

Check that the value entered in the browser matches one of the comma-separated values in CODE, then restart the Deployment after changing the input.

Model requests fail

Verify OPENAI_API_KEY, BASE_URL, Azure settings, and model-provider rate limits. For OpenAI-compatible gateways, confirm that the gateway supports the selected model names.

Balance query is unavailable

Set ENABLE_BALANCE_QUERY to 1 and restart the Deployment.

Additional Resources

License

This Sealos template is provided under the template repository license. NextChat is licensed by its upstream project.

Related templates

Explore more production-ready templates.

More