Model Availability Routing
Model Availability Routing
Chuizi.AI exposes stable public model IDs such as openai/gpt-4.1 or anthropic/claude-sonnet-4-6. Your application calls those public IDs, while the service handles availability checks and backup paths on the server side.
The public contract stays simple: model ID, protocol, request status, usage, cost, latency, and generation ID. Sensitive infrastructure details are not exposed as public API or page content.
Stable contract for integrations
| Contract | Description |
|---|---|
| Model ID | Use the id returned by the model catalog or GET /v1/models |
| Protocol | OpenAI /v1, Anthropic /anthropic, Gemini /gemini |
| Model access range | Manage callable models per key in the console |
| Billing | Each request has a generation ID for cost and usage review |
If you need a fixed model set, configure the current key's model access range in the console instead of depending on server-side implementation details.