Larprouter

https://larprouter.com/docs
Admin
Larprouter is a unified API gateway that allows routing standard OpenAI or Anthropic clients to...
Tokens:1,848
Snippets:21
Trust Score:2.3
Update:2 months ago
Show doc for...
Tokens:
Raw
### GET /models

Source: https://larprouter.com/docs

Retrieves a list of models available to the provided API key.

```APIDOC
## GET /models

### Description
Retrieves a list of models available to the provided API key.

### Method
GET

### Endpoint
/models
```

--------------------------------

### Interact with Posty AI

Source: https://larprouter.com/docs

Examples for sending requests to the Posty AI chat endpoint using curl or JavaScript.

```curl
curl -X POST https://larprouter.com/api/v1/chat   -H "Authorization: Bearer lrsk-your-posty-key"   -H "Content-Type: application/json"   -d '{"message": "Hello Posty!", "model": "posty-2.0-retro"}'
```

```javascript
const response = await fetch('https://larprouter.com/api/v1/chat', {  
  method: 'POST',  
  headers: {  
    'Authorization': 'Bearer lrsk-your-posty-key',  
    'Content-Type': 'application/json',  
  },  
  body: JSON.stringify({  
    message: 'Hello Posty!',  
    model: 'posty-2.0-retro',  
  }),  
});  
  
const data = await response.json();  
console.log(data.model);  
console.log(data.response);
```

--------------------------------

### Perform a streaming request with Python

Source: https://larprouter.com/docs

Configure the OpenAI Python client to point to the LARPROUTER base URL for streaming completions.

```python
from openai import OpenAI

client = OpenAI(
    api_key="lrsk-your-key",
    base_url="https://larprouter.com/api/v1",
)

response = client.chat.completions.create(
    model="MODEL_ID_FROM_CLIENT_MODELS_LIST",
    messages=[{"role": "user", "content": "Hello!"}],
    stream=True,
)

for chunk in response:
    print(chunk.choices[0].delta.content, end="")
```

--------------------------------

### Perform a streaming request with cURL

Source: https://larprouter.com/docs

Use the standard cURL command to interact with the gateway by setting the Authorization header and base URL.

```bash
curl https://larprouter.com/api/v1/chat/completions \
  -H "Authorization: Bearer lrsk-your-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "MODEL_ID_FROM_GET_API_V1_MODELS",
    "messages": [{"role": "user", "content": "Hello!"}],
    "stream": true
  }'
```

--------------------------------

### Perform a streaming request with Node.js

Source: https://larprouter.com/docs

Use the OpenAI Node.js client with the LARPROUTER base URL to handle streaming responses.

```javascript
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "lrsk-your-key",
  baseURL: "https://larprouter.com/api/v1",
});

const stream = await client.chat.completions.create({
  model: "MODEL_ID_FROM_CLIENT_MODELS_LIST",
  messages: [{ role: "user", content: "Hello!" }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}
```

--------------------------------

### Configure Authentication Headers

Source: https://larprouter.com/docs

Use these headers to authenticate requests to the LarpRouter gateway.

```http
Authorization: Bearer lrsk-your-key  
  
# Anthropic-style header also works  
x-api-key: lrsk-your-key
```

--------------------------------

### POST /chat/completions

Source: https://larprouter.com/docs

Provides an OpenAI-compatible chat completion endpoint.

```APIDOC
## POST /chat/completions

### Description
Provides an OpenAI-compatible chat completion endpoint.

### Method
POST

### Endpoint
/chat/completions
```

--------------------------------

### POST /chat/completions

Source: https://larprouter.com/docs

Creates a chat completion request to the specified model. This endpoint is compatible with the standard OpenAI chat completions API.

```APIDOC
## POST /chat/completions

### Description
Sends a chat completion request to the gateway, which routes it to the specified model. Supports streaming responses via Server-Sent Events (SSE).

### Method
POST

### Endpoint
https://larprouter.com/api/v1/chat/completions

### Request Body
- **model** (string) - Required - The ID of the model to use.
- **messages** (array) - Required - A list of message objects containing role and content.
- **stream** (boolean) - Optional - Whether to stream the response.
```

--------------------------------

### POST /chat

Source: https://larprouter.com/docs

Keyless Posty AI chat endpoint for native message requests.

```APIDOC
## POST /chat

### Description
Keyless Posty AI chat endpoint for native message requests.

### Method
POST

### Endpoint
/chat

### Request Body
- **message** (string) - Required - The message content for the AI.
- **model** (string) - Optional - The model ID to use (defaults to posty-1.8-mini).
```

--------------------------------

### POST /messages

Source: https://larprouter.com/docs

Provides an Anthropic-compatible messages endpoint.

```APIDOC
## POST /messages

### Description
Provides an Anthropic-compatible messages endpoint.

### Method
POST

### Endpoint
/messages
```

--------------------------------

### Streaming Gateway Endpoints

Source: https://larprouter.com/docs

The gateway supports streaming responses via server-sent events for OpenAI Chat Completions and Anthropic Messages formats.

```APIDOC
## Streaming

### Description
OpenAI and Anthropic gateway endpoints support streaming over server-sent events. Clients must pass `stream: true` to receive responses as they arrive.

### Usage
- Streams remain open for up to 600 seconds.
- Clients may reconnect if the stream is interrupted.
- Supports OpenAI Chat Completions and Anthropic Messages formats.
```

--------------------------------

### Error Handling

Source: https://larprouter.com/docs

Reference for standard HTTP status codes and machine-readable error types returned by the API.

```APIDOC
## Error Codes

| Status | Type | Meaning | Resolution |
|---|---|---|---|
| 401 | `authentication_error` | Invalid or missing API key | Check the Authorization header |
| 402 | `insufficient_credit` | Account has no credits | Add credit in billing |
| 429 | `rate_limit_error` | Key balance exhausted or too many requests | Back off and retry |
| 503 | `service_unavailable` | Model pool temporarily unavailable | Retry with backoff |
```
Tokens:
Raw