Chat Completions

Chat Communications is the most commonly used dialogue entry in the text series, suitable for chat client, assistant, workflow node and text generation scenes that require streaming output.

API Path

Methodology	Path	Returns by
POST	/v1/chat/completions	synchronous JSON or SSE streaming returned.

Example request

curl https://moonnexai.com/v1/chat/completions \
  -H "Authorization: Bearer <MOONNEXAI_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.6-terra",
    "messages": [
      {
        "role": "system",
        "content": "你是一个简洁的开发者助手。"
      },
      {
        "role": "user",
        "content": "写一句 API 接入成功后的欢迎语。"
      }
    ]
  }'

Common field

field	Annotations
model	Model name. First, you can confirm the available model by Model Query.
messages	Multi-cycle dialogue news array.
temperature	Controls the randomity of the output.
max_tokens	Limit the length of generation.
stream	Use SSE streaming to return when setting true.

Message Structure

role	Purpose
system	Set roles, tone and boundaries.
user	User input.
assistant	Historic assistant responded.

response Processing

scene	Treatment
Normal Return	Reads the generated text in response and saves the request model and track information.
streaming returns	Adds to the SSE event by paragraph, closes the connection after the event has arrived.
request failed	Checks the model name, API Key permission, request body format and context length.

Access Recommendations

• Chat client gives priority to this API, Base URL set to https://moonnexai.com/v1.
• Please pass only the necessary context to avoid the inclusion of irrelevant history in request.
• Set stream: true when you want to generate side displays and process incremental content by SSE events.

Relevant Pages

• Chat and Responses Summary
• Text Model Matrix
• OpenAI-compatible Guide
• API Reference