cURL (Unified Mode) | Enterprise Router

The unified endpoint is POST /v1/chat/completions. It accepts an OpenAI-compatible request body and returns an OpenAI-compatible response, regardless of which provider handles the request.

Basic request

$ curl -X POST https://gateway.example.com/v1/chat/completions \
>   -H "Authorization: Bearer sk-proxy-YOUR_KEY_HERE" \
>   -H "Content-Type: application/json" \
>   -d '{
>     "model": "openai/gpt-4o",
>     "messages": [
>       {"role": "user", "content": "Hello!"}
>     ]
>   }'

Calling Anthropic

$ curl -X POST https://gateway.example.com/v1/chat/completions \
>   -H "Authorization: Bearer sk-proxy-YOUR_KEY_HERE" \
>   -H "Content-Type: application/json" \
>   -d '{
>     "model": "anthropic/claude-sonnet-4-6",
>     "messages": [
>       {"role": "system", "content": "You are a helpful assistant."},
>       {"role": "user", "content": "What is quantum computing?"}
>     ],
>     "max_tokens": 512
>   }'

Calling Gemini

$ curl -X POST https://gateway.example.com/v1/chat/completions \
>   -H "Authorization: Bearer sk-proxy-YOUR_KEY_HERE" \
>   -H "Content-Type: application/json" \
>   -d '{
>     "model": "google/gemini-2.5-flash",
>     "messages": [
>       {"role": "user", "content": "Write a haiku about APIs."}
>     ]
>   }'

Streaming

Add "stream": true to get Server-Sent Events:

$ curl -X POST https://gateway.example.com/v1/chat/completions \
>   -H "Authorization: Bearer sk-proxy-YOUR_KEY_HERE" \
>   -H "Content-Type: application/json" \
>   -N \
>   -d '{
>     "model": "anthropic/claude-sonnet-4-6",
>     "messages": [
>       {"role": "user", "content": "Write a short story."}
>     ],
>     "stream": true
>   }'

The response is a stream of data: lines in OpenAI’s SSE format:

data: {"id":"chatcmpl-...","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"Once"},"finish_reason":null}]}
data: {"id":"chatcmpl-...","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":" upon"},"finish_reason":null}]}
...
data: [DONE]

Tool calling

$ curl -X POST https://gateway.example.com/v1/chat/completions \
>   -H "Authorization: Bearer sk-proxy-YOUR_KEY_HERE" \
>   -H "Content-Type: application/json" \
>   -d '{
>     "model": "openai/gpt-4o",
>     "messages": [
>       {"role": "user", "content": "What is the weather in Tokyo?"}
>     ],
>     "tools": [
>       {
>         "type": "function",
>         "function": {
>           "name": "get_weather",
>           "description": "Get weather for a city",
>           "parameters": {
>             "type": "object",
>             "properties": {
>               "city": {"type": "string"}
>             },
>             "required": ["city"]
>           }
>         }
>       }
>     ],
>     "tool_choice": "auto"
>   }'

Response format

All responses follow the OpenAI chat completion format:

1 {
2   "id": "chatcmpl-abc123",
3   "object": "chat.completion",
4   "model": "anthropic/claude-sonnet-4-6",
5   "choices": [
6     {
7       "index": 0,
8       "message": {
9         "role": "assistant",
10         "content": "Hello! How can I help you today?"
11       },
12       "finish_reason": "stop"
13     }
14   ],
15   "usage": {
16     "prompt_tokens": 12,
17     "completion_tokens": 9,
18     "total_tokens": 21
19   }
20 }

The model field in the response reflects the provider and model that handled the request (e.g., anthropic/claude-sonnet-4-6 or google/gemini-2.5-flash).