Endpoint

POST /api/chat

Send chat messages to AI models. This endpoint routes your requests to the configured AI providers and returns the response. Supports system context messages for better control.

POST /api/chat

Send chat messages to AI models with optional system context.

Active

Request Body

{
  "model": "string (optional, default: 'google/gemini-2.5-flash')",
  "responsetype": "string (optional, default: 'stream')",
  "messages": [
    {
      "role": "user | system",
      "prompt": "string (required)"
    }
  ]
}

model: The AI model to use. Format: provider/model-name (e.g., google/gemini-2.5-flash)

responsetype: Response format type. Currently supports "stream"

messages: Array of message objects. Each message must have:

role: "user" - User messages that form the main prompt
role: "system" - System messages used as context/instructions
prompt: The message content (required)

Note: System messages are combined and used as context. At least one user message is required.

Example Request (Basic)

curl -X POST https://api.nextcraftai.com/v1/chat \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-2.5-flash",
    "responsetype": "stream",
    "messages": [
      {
        "role": "user",
        "prompt": "What is the date and time today"
      }
    ]
  }'

Example Request (With System Context)

curl -X POST https://api.nextcraftai.com/v1/chat \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-2.5-flash",
    "responsetype": "stream",
    "messages": [
      {
        "role": "system",
        "prompt": "You are a helpful assistant that provides accurate information."
      },
      {
        "role": "user",
        "prompt": "What is the date and time today"
      }
    ]
  }'

System messages provide context and instructions to the AI model. They are combined and prepended to user messages.

Response Format

{
  "id": "7d52dacc-83f9-404f-b1e1-f00d3382453e",
  "created": 1763369195,
  "model": "google/gemini-2.5-flash",
  "responsetype": "stream",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "I'm sorry, but I do not have access to real-time information, including the current date and time. My knowledge cut-off is **June 2024**.\n\nTo find out the current date and time, please check your device's clock."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 7,
    "completion_tokens": 56,
    "total_tokens": 63
  }
}

id: Unique identifier for this request

created: Unix timestamp when the response was created

model: The model that processed the request

choices: Array containing the AI's response

usage: Token usage statistics (prompt_tokens, completion_tokens, total_tokens)