5. Chat Completions#
POST /v1/chat/completions — the core endpoint, compatible with OpenAI Chat Completions.
Request parameters#
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | Yes | Model name, e.g. gpt-4o, claude-3-5-sonnet-20241022 |
messages | array | Yes | Message array; each item contains role (system/user/assistant) and content |
stream | boolean | No | Whether to stream the response; defaults to false |
temperature | number | No | Sampling temperature; higher means more random |
max_tokens | integer | No | Maximum number of tokens to generate |
Other standard OpenAI parameters (
top_p,presence_penalty, etc.) are passed through to the upstream model.
Non-streaming request#
cURL
curl http://183.240.79.21:52099/v1/chat/completions \
-H "Authorization: Bearer sk-你的YiTuoToken-Key" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-4o",
"messages": [
{ "role": "system", "content": "你是一个乐于助人的助手。" },
{ "role": "user", "content": "你好，请介绍一下你自己" }
],
"temperature": 0.7
}'
Streaming request (SSE)#
Add "stream": true to the request body. The response arrives incrementally as Server-Sent Events; each event is a chat.completion.chunk, and the stream ends with data: [DONE].
cURL
curl http://183.240.79.21:52099/v1/chat/completions \
-H "Authorization: Bearer sk-你的YiTuoToken-Key" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-4o",
"messages": [{ "role": "user", "content": "写一首关于秋天的短诗" }],
"stream": true
}'
Multi-turn conversations#
Append prior messages, in order, to the messages array to keep context:
JSON
{
"model": "gpt-4o",
"messages": [
{ "role": "user", "content": "推荐一部科幻电影" },
{ "role": "assistant", "content": "推荐《星际穿越》。" },
{ "role": "user", "content": "它的导演是谁？" }
]
}