Chat Completion API

Send messages to AI models and receive responses

Create Chat Completion

POST/api/chat

Request Body

Parameter	Type	Required	Description
messages	array	Yes	Array of message objects with role and content
model	string	No	Model ID to use. Default: gpt-4o-mini
stream	boolean	No	Enable streaming response. Default: false
systemPrompt	string	No	Custom system prompt to prepend
temperature	number	No	Creativity level 0-2. Default: 0.7
maxTokens	number	No	Maximum tokens in response. Default: 4096

Message Object

Field	Type	Description
role	string	"user", "assistant", or "system"
content	string	The message content

Example Request

curl -X POST https://your-domain.com/api/chat \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "messages": [
      { "role": "user", "content": "Explain quantum computing in simple terms" }
    ],
    "model": "gpt-4o",
    "temperature": 0.7
  }'

Example Response

{
  "success": true,
  "data": {
    "id": "chat_abc123",
    "model": "gpt-4o",
    "message": {
      "role": "assistant",
      "content": "Quantum computing uses quantum bits (qubits) that can exist in multiple states simultaneously..."
    },
    "usage": {
      "promptTokens": 12,
      "completionTokens": 156,
      "totalTokens": 168
    },
    "creditsUsed": 2
  }
}

Streaming Response

Enable streaming to receive tokens as they are generated. Useful for real-time chat interfaces.

Example Streaming Request

curl -X POST https://your-domain.com/api/chat \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "messages": [
      { "role": "user", "content": "Write a haiku about coding" }
    ],
    "stream": true
  }'

Streaming Response Format

data: {"delta": "Lines", "done": false}
data: {"delta": " of", "done": false}
data: {"delta": " code", "done": false}
data: {"delta": " flow", "done": false}
...
data: {"delta": "", "done": true, "usage": {"totalTokens": 45}}

Available Models

gpt-4oOpenAI

Most capable GPT-4 model with vision support

gpt-4o-miniOpenAI

Fast and affordable GPT-4 variant

claude-3-5-sonnetAnthropic

Excellent for complex tasks and coding

claude-3-haikuAnthropic

Fast responses for simple tasks

gemini-2.0-flashGoogle

Advanced multimodal reasoning

deepseek-chatDeepSeek

Cost-effective alternative

Error Codes

Code	Description
400	Invalid request body or missing required fields
401	Invalid or missing API key
402	Insufficient credits
404	Model not found or unavailable
429	Rate limit exceeded
500	Internal server error

Docs APIChat