Providers
Connect to 25+ AI providers. Users configure them once, your app uses them automatically.
Providers are AI service adapters that connect WebInfer to different AI backends—cloud APIs, local runners, and gateways.
For users: Configure providers once in the extension or native app. Add API keys, set priorities, and WebInfer handles the rest.
For developers: You don't manage providers. When your app calls generateText(), WebInfer automatically routes to the user's configured providers.
Provider Types
Cloud APIs
Direct connections to AI providers like OpenAI, Anthropic, Google, and Mistral. Users add their own API keys.
Local Runners
Run models on your own hardware with Ollama or LM Studio. Complete privacy, zero external data sharing.
Aggregators
Services like OpenRouter and Portkey that provide access to 100+ models through a single API key.
Gateways
Self-hosted or cloud WebInfer endpoints. Developers can provide courtesy compute to users via gateways.
Supported Providers
How Provider Selection Works
When your app makes an AI request, WebInfer's routing engine automatically selects the best provider based on:
- •Task type — text, image, audio, code generation
- •User priorities — preferred providers, cost vs quality tradeoffs
- •Model capabilities — context length, multimodal support, specialized skills
- •Availability — fallback to next provider if one fails
Add Provider from URL
WebInfer supports auto-discovery of gateways and daemons. Paste a URL and WebInfer automatically fetches the provider's capabilities and configuration.
In-App Discovery
Go to Settings → Integrations and click "Add from URL".
CLI Discovery
Add providers via CLI with automatic discovery.
webinfer provider add https://llm.acme.comDiscovery works with:
Configuring Providers (Users)
Next Steps
Add API keys and set priorities
Settings → Integrations →Provide courtesy compute to your users
Gateway Docs →