feat: add OrcaRouter as a first-class language model provider

site/src/docs/examples.md

@@ -92,6 +92,13 @@ AZURE_OPENAI_ENDPOINT=...
 AZURE_OPENAI_API_KEY=...
 ```
 
+The examples also work against any OpenAI-compatible gateway, such as [OrcaRouter](https://www.orcarouter.ai), by pointing `OPENAI_ENDPOINT` at the gateway's Chat Completions URL in addition to the OpenAI variables above:
+
+```
+# Optional: use an OpenAI-compatible gateway instead of api.openai.com
+OPENAI_ENDPOINT=https://api.orcarouter.ai/v1/chat/completions
+```
+
 ## Step 4: Run the examples
 
 Examples can be found in the `typescript/examples` directory.

site/src/docs/python/basic-usage.md

@@ -83,7 +83,7 @@ def create_azure_openai_language_model(api_key: str, endpoint: str): ...
 For even more convenience, TypeChat also provides a function to infer whether
 you're using OpenAI or Azure OpenAI.
 
-```ts
+```py
 def create_language_model(
     vals: dict[str, str | None]
 ) -> TypeChatLanguageModel: ...
@@ -94,6 +94,29 @@ pass them in.
 Based on whether `OPENAI_API_KEY` or `AZURE_OPENAI_API_KEY` is set, you'll get
 a model of the appropriate type.
 
+#### Using OpenAI-compatible gateways
+
+TypeChat works with any service that exposes the OpenAI Chat Completions API.
+To use a gateway such as [OrcaRouter](https://www.orcarouter.ai) or OpenRouter,
+point `create_openai_language_model` at the gateway's endpoint via the
+`endpoint` argument:
+
+```py
+model = create_openai_language_model(
+    api_key, model, endpoint="https://api.orcarouter.ai/v1/chat/completions"
+)
+```
+
+With `create_language_model`, set the `OPENAI_ENDPOINT` environment variable to
+the gateway's Chat Completions URL alongside `OPENAI_API_KEY` and
+`OPENAI_MODEL`:
+
+```
+OPENAI_API_KEY=<your API key>
+OPENAI_MODEL=<model name>
+OPENAI_ENDPOINT=https://api.orcarouter.ai/v1/chat/completions
+```
+
 The `TypeChatLanguageModel` returned by these functions has a few writable
 attributes you might find useful:
 

site/src/docs/typescript/basic-usage.md

@@ -68,7 +68,7 @@ For convenience, TypeChat provides two functions out of the box to connect to th
 You can call these directly.
 
 ```ts
-export function createOpenAILanguageModel(apiKey: string, model: string, endPoint? string): TypeChatLanguageModel;
+export function createOpenAILanguageModel(apiKey: string, model: string, endPoint?: string): TypeChatLanguageModel;
 
 export function createAzureOpenAILanguageModel(apiKey: string, endPoint: string): TypeChatLanguageModel;
 ```
@@ -82,6 +82,27 @@ export function createLanguageModel(env: Record<string, string | undefined>): Ty
 With `createLanguageModel`, you can populate your environment variables and pass them in.
 Based on whether `OPENAI_API_KEY` or `AZURE_OPENAI_API_KEY` is set, you'll get a model of the appropriate type.
 
+#### Using OpenAI-compatible gateways
+
+TypeChat works with any service that exposes the OpenAI Chat Completions API.
+To use a gateway such as [OrcaRouter](https://www.orcarouter.ai) or OpenRouter,
+point `createOpenAILanguageModel` at the gateway's endpoint via the `endPoint`
+argument:
+
+```ts
+const model = createOpenAILanguageModel(apiKey, model, "https://api.orcarouter.ai/v1/chat/completions");
+```
+
+With `createLanguageModel`, set the `OPENAI_ENDPOINT` environment variable to
+the gateway's Chat Completions URL alongside `OPENAI_API_KEY` and
+`OPENAI_MODEL`:
+
+```
+OPENAI_API_KEY=<your API key>
+OPENAI_MODEL=<model name>
+OPENAI_ENDPOINT=https://api.orcarouter.ai/v1/chat/completions
+```
+
 Regardless, of how you decide to construct your model, it is important to avoid committing credentials directly in source.
 One way to make this work between production and development environments is to use a `.env` file in development, and specify that `.env` in your `.gitignore`.
 You can use a library like [`dotenv`](https://www.npmjs.com/package/dotenv) to help load these up.