AI 模型流式生成的 Chat Completion 响应对象块数据Documentation Index
Fetch the complete documentation index at: https://platform.stepfun.com/docs/llms.txt
Use this file to discover all available pages before exploring further.
属性
-
idstring
生成的聊天响应 ID -
objectstring
模型生成聊天响应的模式，此模式下总为chat.completion.trunk -
createdtimestamp
聊天响应时的 Unix 时间戳，单位为秒 -
modelstring
模型名称 -
choicesobject array
模型流式生成的聊天响应结果的可选路径列表。单个choiceobject 属性：显示 子属性
finish_reasonstring
模型停止继续生成的原因indexint
当前可选路径序列号deltaobject
模型渐进生成的聊天响应块
显示 子属性
rolestring
消息所属角色，此处总为assistantcontentstring
消息文本内容reasoningstring
推理思考过程内容，仅在 step 推理模型下返回。tool_callsobject arrayoptional
toolcall 内容返回
显示 子属性
idstring
函数执行 ID，由模型生成，在 context 保持唯一。typestring
toolcall 的类型，默认为functionfunctionobject
函数的消息体
显示 子属性
namestring
函数名称，通常纯英文、数字和_-符号，一般是在上一轮对话提交的 tools 列表中argumentsstring
函数执行的参数，一般为 json 结构化对象。
-
usageobject
模型聊天响应生成的标记统计信息显示 子属性
prompt_tokensint
生成过程中使用的提示信息总标记数量cached_tokensintoptional
生成过程中使用的提示信息被缓存的总标记数量completion_tokensint
生成的响应消息内容总标记数量total_tokensint
生成结束后统计的总的标记数量
示例
data: {"id":"d7ae7c4a-1524-4fe5-9d58-e4d59b89d8f0","object":"chat.completion.chunk","created":1709899323,"model":"step-1-8k","choices":[{"index":0,"delta":{"role":"","content":"您"},"finish_reason":""}],"usage":{"prompt_tokens":83,"completion_tokens":1,"total_tokens":84}}
data: {"id":"d7ae7c4a-1524-4fe5-9d58-e4d59b89d8f0","object":"chat.completion.chunk","created":1709899323,"model":"step-1-8k","choices":[{"index":0,"delta":{"role":"","content":"好"},"finish_reason":""}],"usage":{"prompt_tokens":83,"completion_tokens":2,"total_tokens":85}}
data: {"id":"d7ae7c4a-1524-4fe5-9d58-e4d59b89d8f0","object":"chat.completion.chunk","created":1709899323,"model":"step-1-8k","choices":[{"index":0,"delta":{"role":"","content":"！"},"finish_reason":""}],"usage":{"prompt_tokens":83,"completion_tokens":3,"total_tokens":86}}
data: {"id":"d7ae7c4a-1524-4fe5-9d58-e4d59b89d8f0","object":"chat.completion.chunk","created":1709899323,"model":"step-1-8k","choices":[{"index":0,"delta":{"role":"","content":"阶"},"finish_reason":""}],"usage":{"prompt_tokens":83,"completion_tokens":4,"total_tokens":87}}
data: {"id":"d7ae7c4a-1524-4fe5-9d58-e4d59b89d8f0","object":"chat.completion.chunk","created":1709899323,"model":"step-1-8k","choices":[{"index":0,"delta":{"role":"","content":"跃"},"finish_reason":""}],"usage":{"prompt_tokens":83,"completion_tokens":5,"total_tokens":88}}
...
data: {"id":"d7ae7c4a-1524-4fe5-9d58-e4d59b89d8f0","object":"chat.completion.chunk","created":1709899323,"model":"step-1-8k","choices":[{"index":0,"delta":{"role":"","content":"更多的"},"finish_reason":""}],"usage":{"prompt_tokens":83,"completion_tokens":147,"total_tokens":230}}
data: {"id":"d7ae7c4a-1524-4fe5-9d58-e4d59b89d8f0","object":"chat.completion.chunk","created":1709899323,"model":"step-1-8k","choices":[{"index":0,"delta":{"role":"","content":"价值"},"finish_reason":""}],"usage":{"prompt_tokens":83,"completion_tokens":148,"total_tokens":231}}
data: {"id":"d7ae7c4a-1524-4fe5-9d58-e4d59b89d8f0","object":"chat.completion.chunk","created":1709899323,"model":"step-1-8k","choices":[{"index":0,"delta":{"role":"","content":"。"},"finish_reason":""}],"usage":{"prompt_tokens":83,"completion_tokens":149,"total_tokens":232}}
data: {"id":"d7ae7c4a-1524-4fe5-9d58-e4d59b89d8f0","object":"chat.completion.chunk","created":1709899323,"model":"step-1-8k","choices":[{"index":0,"delta":{"role":"","content":""},"finish_reason":""}],"usage":{"prompt_tokens":83,"completion_tokens":150,"total_tokens":233}}
data: {"id":"d7ae7c4a-1524-4fe5-9d58-e4d59b89d8f0","object":"chat.completion.chunk","created":1709899323,"model":"step-1-8k","choices":[{"index":0,"delta":{"role":"","content":""},"finish_reason":"stop"}],"usage":{"prompt_tokens":83,"completion_tokens":150,"total_tokens":233}}
data: [DONE]