Create Chat Completion

• Endpoint: POST https://api.olddog.shop/v1/chat/completions
• Authentication: Authorization: Bearer <API_KEY>
• Content-Type: application/json

Generate a model response from a list of chat messages (compatible with OpenAI chat.completions).

Request parameters

Name	Type	Required	Description
model	string	Yes	Model ID, e.g. gpt-4o-mini (subject to what’s available in the console).
messages	array	Yes	Chat message list. Each item includes role and content.
temperature	number	No	Sampling temperature, typically (0~2). Higher is more random.
top_p	number	No	Nucleus sampling probability, typically (0~1). Usually tune either this or temperature.
max_tokens	integer	No	Maximum tokens to generate (limits vary by model).
stream	boolean	No	Enable streaming. Default false.
stop	string / array	No	Stop sequence(s). Generation stops early when matched.
presence_penalty	number	No	Topic novelty penalty, typically (-2~2).
frequency_penalty	number	No	Repetition penalty, typically (-2~2).
user	string	No	End-user identifier for abuse monitoring and analytics.

messages fields

Field	Type	Required	Description
role	string	Yes	system / user / assistant / tool.
content	string / array	Yes	Text content, or a multimodal content array (if supported by the model).
name	string	No	Optional author name (compat field).

cURL example

curl --request POST "https://api.olddog.shop/v1/chat/completions" \
  --header "Authorization: Bearer $OLD_DOG_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "model": "gpt-4o-mini",
    "messages": [
      { "role": "system", "content": "你是一个专业的中文技术写作助手。" },
      { "role": "user", "content": "用三句话解释什么是向量嵌入。" }
    ],
    "temperature": 0.7
  }'