Chat Completions

Create a chat completion using the Vexrail API. This endpoint is compatible with the OpenAI chat completions format and supports both streaming and non-streaming responses.

Endpoint

POST /v1/chat/completions

Authentication

Requires x-publishable-key and x-secret-key headers. See Authentication.

Request Body

Field	Type	Required	Description
model	string	Yes	The model to use for the completion. See Models for available options.
messages	array	Yes	An array of message objects representing the conversation history.
stream	boolean	No	If true, the response is streamed as Server-Sent Events. Default: false.
temperature	number	No	Sampling temperature between 0 and 2. Higher values make output more random.
max_tokens	number	No	Maximum number of tokens to generate in the response.
top_p	number	No	Nucleus sampling parameter. An alternative to temperature.

Message Object

Field	Type	Description
role	string	The role of the message author: system, user, or assistant.
content	string	The content of the message.

Non-Streaming Response

Example Request

curl -X POST https://api.vexrail.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "x-publishable-key: pk_live_your_key" \
  -H "x-secret-key: sk_live_your_key" \
  -H "x-conversation-id: conv-123" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What tools can help me manage my projects?"}
    ]
  }'

Example Response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1700000000,
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "There are several great project management tools available..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 150,
    "total_tokens": 175
  }
}

Streaming Response

To receive a streaming response, set stream: true in the request body. The response uses Server-Sent Events (SSE).

Example Request

curl -X POST https://api.vexrail.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "x-publishable-key: pk_live_your_key" \
  -H "x-secret-key: sk_live_your_key" \
  -H "x-conversation-id: conv-123" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {"role": "user", "content": "What tools can help me manage my projects?"}
    ],
    "stream": true
  }'

Example Response

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","created":1700000000,"model":"gpt-4o-mini","choices":[{"index":0,"delta":{"role":"assistant","content":"There"},"finish_reason":null}]}

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","created":1700000000,"model":"gpt-4o-mini","choices":[{"index":0,"delta":{"content":" are"},"finish_reason":null}]}

...

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","created":1700000000,"model":"gpt-4o-mini","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}

data: [DONE]

Conversation Tracking

Include the x-conversation-id header to group messages into a conversation. This enables:

• Better contextual relevance for product promotions.
• Conversation analytics in your dashboard.

If you omit this header, each request is treated as an independent interaction.

Promotions in Responses

When monetization is enabled on your project and relevant advertiser products match the conversation context, the AI response may include contextual product recommendations. These are included naturally within the response content -- no additional parsing is needed on your end.

Error Codes

Status	Description
400	Invalid request body (missing model, empty messages, etc.)
401	Authentication failed
403	Domain not verified or insufficient credit balance
500	Internal server error

See Errors for details.