Balanced
DefaultCost-aware routing for everyday work: reading, small edits, tests.
- Fast, efficient models by default
- Escalate per request when needed
- Usage metered per token
Gateway
One account. Every provider.
The Kete gateway sits between your tools and the model providers. Switch models per task without switching accounts.
Surfaces
VS Code
CLI
JetBrains Soon
Windsurf Soon
Gateway
Kete gateway
- auth · kete login
- route · tier → model
- keys · managed or yours
- meter · usage to portal
Providers
Anthropic
OpenAI
Google Gemini
OpenAI-compatible
01
Request
A surface sends the task, the mode and the context it gathered.
02
Route
The gateway resolves the model: an explicit choice, the mode's default, or your tier.
03
Call
The request goes to the provider with Kete-managed credentials or your own key.
04
Meter
Tokens and cost are recorded against your account and shown in the portal.
Model gateway
Route every request to the right model.
One account, every provider. Choose a tier as the default and override it per mode or per request.
Frontier
Most capableThe most capable models from each provider for large refactors and hard bugs.
- Claude, GPT and Gemini flagships
- Long-context tasks
- Pick per mode or per request
Bring your own
Your keysUse your provider keys or any OpenAI-compatible endpoint through the same agent.
- Anthropic, OpenAI, Gemini keys
- Self-hosted or third-party endpoints
- Usage still visible in the portal
Providers
Supported providers
| Provider | Models | Your own key | Status |
|---|---|---|---|
| Anthropic | Claude family | Available | |
| OpenAI | GPT family | Available | |
| Gemini family | Available | ||
| OpenAI-compatible | Any endpoint implementing the OpenAI API | Available |
Ready to ship faster?
Install in a minute. Keep your editor. Choose your model.
$ npm i -g @ketecode/cli && kete login