Create a Chat Completion¶

Submit conversation messages and receive a generated reply.

POST https://token.moi.matrixorigin.cn/v1/chat/completions

Before you begin¶

Prepare a personal access token or service account API key for Genesis. See Access credentials for credential selection and permissions.
Use List callable models to select a model that supports Chat Completions.

Request body¶

Replace $GENESIS_ACCESS_TOKEN and $MODEL_ID with your credential and the selected model ID.

Request example

curl -X POST \
  "https://token.moi.matrixorigin.cn/v1/chat/completions" \
  -H "Authorization: Bearer $GENESIS_ACCESS_TOKEN" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "'"$MODEL_ID"'",
  "messages": [
    {
      "role": "user",
      "content": "Reply with OK."
    }
  ],
  "max_tokens": 64
}'

Parameters

The table covers text conversation fields. Fields for image input and tool calls are not expanded here.

Parameter	Type	Required	Description
`model`	string	Yes	Selected model ID from `data[].id` in the model list.
`messages`	array of object	Yes	Nonempty messages in conversation order.
`messages[].role`	string	Yes	Use `system`, `user`, or `assistant` for text conversations.
`messages[].content`	string or array of object	No	Text or text blocks.
`messages[].content[].type`	string	Required for a text block	Use `text` for a text block.
`messages[].content[].text`	string	Required for a text block	Nonempty text content.
`max_tokens`	integer	No	Output token limit; reasoning models may also use this budget for reasoning tokens. Use a model-supported value.
`temperature`	number	No	Sampling temperature, when supported by the model.
`top_p`	number	No	Nucleus sampling parameter, when supported by the model.
`stream`	boolean	No	Set to `true` for streaming deltas.

Successful response¶

Response example

{
  "id": "chatcmpl-example",
  "object": "chat.completion",
  "model": "MODEL_ID",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "OK"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 1,
    "total_tokens": 13
  }
}

Fields

Field	Type	Description
`id`	string	Completion identifier.
`object`	string	Object type `chat.completion`.
`model`	string	Model that processed the request.
`choices`	array of object	Generated choices.
`choices[].index`	integer	Zero-based choice index.
`choices[].message`	object	Generated assistant message.
`choices[].message.role`	string	Message role `assistant`.
`choices[].message.content`	string or null	Generated text; it can be null in non-text results.
`choices[].finish_reason`	string or null	Stop reason; `stop` indicates a normal stop and `length` a length limit.
`usage`	object	Token usage returned by the model.
`usage.prompt_tokens`	integer	Input tokens.
`usage.completion_tokens`	integer	Generated tokens.
`usage.total_tokens`	integer	Total input and generated tokens.

Streaming response¶

Set stream to true in the request body to receive generated content incrementally. The service sends server-sent events (SSE) and ends the response with data: [DONE].

Request example

curl -N -X POST \
  "https://token.moi.matrixorigin.cn/v1/chat/completions" \
  -H "Authorization: Bearer $GENESIS_ACCESS_TOKEN" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "'"$MODEL_ID"'",
  "messages": [
    {
      "role": "user",
      "content": "Reply with OK."
    }
  ],
  "max_tokens": 64,
  "stream": true
}'

Response example

data: {"object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"OK"},"finish_reason":null}]}

data: {"object":"chat.completion.chunk","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}

data: [DONE]

Fields

Field	Type	Description
`choices[].index`	integer	Choice index used to distinguish generated results.
`choices[].delta.content`	string	Incremental text to append to the corresponding result in receive order.
`choices[].finish_reason`	string or null	Reason the corresponding result ended; `null` while generation is in progress.

Parse complete SSE events. A network read can contain part of an event or multiple events, so buffer data before parsing. If the connection closes before data: [DONE], the content received so far may be incomplete.

Error response¶

A missing model ID returns HTTP 400. Supply the model ID before sending the request again.

Response example

{
  "error": {
    "message": "missing required parameter: model",
    "type": "invalid_request",
    "code": "invalid_request"
  }
}

Fields

Field	Type	Description
`error`	object	Error details.
`error.message`	string	Error description; the example indicates a missing model ID.
`error.type`	string	Error type; may be omitted by a model service.
`error.code`	string or null	Error code; may be omitted by a model service.

Last updated on Oct 19, 2026