# __PROVIDER_ID__ provider

> Scaffold stub — replace with docs-verified provider documentation before publishing.

## What it does

`__PACKAGE_NAME__` is an OpenAI-compatible provider package for Prism
(chat-completions style). It builds on `createOpenAICompatibleProvider` from
`@arnilo/prism/providers/openai-compatible`.

## When to use it

Use it for OpenAI-compatible endpoints that follow the Chat Completions
convention. Skip it for providers with bespoke serialization or auth.

## Inputs / request

- Base URL: `__BASE_URL__` (`--base-url` at scaffold time).
- Auth: `api_key` auth method; hosts resolve the credential value (e.g. from
  `__ENV_KEY__`).

## Outputs / response / events

Standard `ProviderEvent` stream: `content_delta`, `done` (with usage), or
`error`. Tool calls arrive as deltas and are reconstructed by the host.

## Request/response example

```ts
import { createResolver } from "@arnilo/prism";
import { create__PROVIDER_PASCAL__ProviderPackage } from "__PACKAGE_NAME__";

const resolver = createResolver();
resolver.registerProviderPackage(
  create__PROVIDER_PASCAL__ProviderPackage({ apiKey: () => process.env.__ENV_KEY__ }),
);
```

## Implementation example

`src/provider.ts` calls `createOpenAICompatibleProvider` with the scaffolded
base URL, api key, and `doneUsage: true`. Model metadata lives in `src/models.ts`;
cache-hint mapping helpers live in `src/cache.ts`.

## Extension and configuration notes

- Override `baseUrl`, `id`, `models`, `apiKey`, and `fetch` per provider
  package/instance.
- Cache behavior is scaffolded as `cache: { kind: "implicit" }` — confirm
  against the provider's actual caching before relying on it.

## Security and performance notes

- API keys are host-resolved credentials; generated code stores no secrets.
- Cache keys are identifiers only, sanitized via shared core helpers.

## Related APIs

- [OpenAI-compatible provider base](../../providers/openai-compatible.md)
- [Provider conformance](../../provider-conformance.md)
- [Provider layer](../../provider-layer.md)