dola-seed-2-1-turbo-260628 Chat Completions

Invoke BytePlus chat completions capability.

Supported models include dola-seed-2-1-turbo-260628.

Documented fields: model, messages, stream, stream_options.include_usage, stream_options.chunk_include_usage, max_completion_tokens, response_format, frequency_penalty, presence_penalty, temperature, top_p, tools, parallel_tool_calls, tool_choice.messages[].content supports plain text; assistant messages support tool_calls.

POST /v1/chat/completions

cURL

basic_text_chat

curl --request POST \ --url https://baze-api.powerbuyin.top/v1/chat/completions \ --header 'Authorization: Bearer <token>' \ --header 'Content-Type: application/json' \ --data ' { "model": "dola-seed-2-1-turbo-260628", "messages": [ { "role": "system", "content": "You are a concise and accurate assistant." }, { "role": "user", "content": "Summarize the core process of RAG in three sentences." } ], "temperature": 0.3, "max_completion_tokens": 1024, "stream": false } '

200

{
  "id": "chatcmpl_bp_123",
  "object": "chat.completion",
  "created": 1742342400,
  "model": "dola-seed-2-1-turbo-260628",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The core process of RAG typically involves three steps: retrieval, augmentation, and generation. The system first converts the user's question into a vector and retrieves relevant knowledge fragments, then concatenates the retrieval results with the original question into the prompt. Finally, the model generates an answer based on the augmented context, thereby reducing hallucinations and improving factual accuracy."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 123,
    "completion_tokens": 98,
    "total_tokens": 221
  }
}

Authorizations

Authorization · string · header · required

Pass Authorization: Bearer <token> in the request header.

Body

application/json

BytePlus chat completions request body.

model · enum<string> · required

Model name. Supported BytePlus chat models include dola-seed-2-1-turbo-260628

Available options: dola-seed-2-1-turbo-260628

Example:

"dola-seed-2-1-turbo-260628"

messages · object[] · required

Message list. This document exposes four roles: system, user, assistant, tool. messages[].content supports plain text.

Minimum array length: 1

Show child attributes

stream · boolean · default: true

Whether to enable streaming output. When true, the response content type is text/event-stream.

stream_options · object

Additional options for streaming response. Only effective when stream=true.

Show child attributes

max_completion_tokens · integer

Maximum length of the model response, in tokens.

response_format · object

Controls the answer format (Beta).

Show child attributes

frequency_penalty · number · default: 0

Frequency penalty. The higher the value, the more it suppresses repetitive expressions.

Required range: -2 <= x <= 2

presence_penalty · number · default: 0

Presence penalty. The higher the value, the more it encourages the model to introduce new topics.

Required range: -2 <= x <= 2

temperature · number · default: 1

Sampling temperature. Lower values make the output more stable, higher values make it more creative.

Required range: 0 <= x <= 2

top_p · number · default: 0.95

Nucleus sampling parameter. Usually used as an alternative to temperature.

Required range: 0 <= x <= 1

tools · object[]

List of function tool definitions available for the model to call.

Show child attributes

parallel_tool_calls · boolean

Whether to allow the model to initiate multiple tool calls in parallel.

tool_choice · enum<string> object

Tool calling strategy. Can be a string mode or an object specifying a specific function.

Available options: none, auto, required

Response

200

application/json

Success. Returns JSON in non-streaming mode; SSE event stream in streaming mode.

BytePlus chat completions success response.

id · string

Response ID.

object · string

Object type, e.g., chat.completion.

created · integer

Unix timestamp.

model · string

The actual model name used.

choices · object[]

Show child attributes

usage · object

Token usage statistics.

Show child attributes