Chat Completions API

POST /v1/chat/completions is the most commonly used endpoint for multi-turn conversations with language models.

Request

POST https://real200.com/v1/chat/completions

Headers

Header	Type	Required	Description
Authorization	string	Yes	Bearer sk-real200-xxx
Content-Type	string	Yes	application/json

Body Parameters

Parameter	Type	Required	Default	Description
model	string	Yes	-	Model name, e.g., gpt-4o, claude-sonnet-4
messages	array	Yes	-	Conversation message list
temperature	number	No	1.0	Randomness, range 0–2
top_p	number	No	1.0	Nucleus sampling threshold
max_tokens	integer	No	Model default	Maximum generation tokens
stream	boolean	No	false	Enable streaming output

Example Request

curl https://real200.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $REAL200_API_KEY" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "user", "content": "Introduce yourself in three sentences."}
    ],
    "temperature": 0.7,
    "max_tokens": 200
  }'

Response

Non-Streaming Response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1716300000,
  "model": "gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "I am an AI assistant..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 45,
    "total_tokens": 57
  }
}

Streaming Response

When stream: true is enabled, responses are returned in text/event-stream format.

Error Codes

HTTP Status	Error Type	Description
400	invalid_request_error	Request parameter error
401	invalid_api_key	Invalid API Key
402	insufficient_quota	Insufficient balance or quota
429	rate_limit_exceeded	Request rate limit exceeded
500	api_error	Server error

See Error Code Dictionary.