POST/v1/chat/completionsOpenAI Compatible

Chat Completions

Create a chat completion. Fully compatible with the OpenAI Chat Completions API. Just change the base URL and API key.

Compatibility

OpenAI SDK

Streaming

SSE Supported

Auth

Bearer Token

Parameters

Parameter	Type	Required	Description
`model`	string	Required	Model ID. See Models & Pricing for the full list.
`messages`	array	Required	Array of {role, content}. Roles: system, user, assistant.
`temperature`	number	Optional	Sampling temperature 0-2. Higher = more creative. Default: 1.
`max_tokens`	number	Optional	Maximum tokens in the response. Varies by model.
`stream`	boolean	Optional	Enable SSE streaming for real-time tokens. Default: false.
`top_p`	number	Optional	Nucleus sampling parameter. 0-1.
`tools`	array	Optional	Function definitions for tool calling (OpenAI format).
`thinking`	object	Optional	Extended thinking for Claude models. {type: "enabled", budget_tokens: 2000}.

Response Format

200 OK — application/json

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "model": "gpt-5.5",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "Quantum computing uses..."
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 50,
    "total_tokens": 75
  }
}

Examples

curl https://api.aipilotads.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "gpt-5.5",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Explain quantum computing in simple terms."}
    ],
    "temperature": 0.7,
    "max_tokens": 1024
  }'

Streaming Guide → Error Handling → Function Calling →