Doubao Seed
Endpoint: https://mmu.vod-qcloud.com/v1认证: VOD ApiToken / Bearer
Doubao Seed 是文本生成 / 对话模型,部分版本(如 st-2.0-mini、st-2.1-pro)支持图片输入。通过兼容 OpenAI 的接口调用,支持 Chat Completions、Responses 与 Messages 协议及 JSON / SSE 流式响应,另有角色扮演类版本 st-character。
基本信息
| 项目 | 取值 |
|---|---|
| 调用地址 | https://mmu.vod-qcloud.com |
| 认证 | VOD 应用签发的 ApiToken / Bearer |
| 输出 | 文本 / 结构化响应 |
| 响应方式 | JSON / SSE |
支持的协议
| 规格 | 路径 | 对象 |
|---|---|---|
| Chat Completions | POST /v1/chat/completions | 下方所有模型 |
| Responses | POST /v1/responses | 下方所有模型 |
| Messages | POST /v1/messages | 下方所有模型 |
下方模型 ID 使用对应规格。认证与公共字段遵循 API Reference。
采样选项
对本文档中列出的所有模型通用。
| 参数 | 设置 |
|---|---|
temperature | 可设置 |
top_p | 可设置 |
temperature 指定采样温度,top_p 指定累积概率范围。以一种方式为主进行调整。
各版本推理设置
| 模型 ID | 设置方式 | 停用 |
|---|---|---|
st-evolving | thinking_enabled | false |
st-character | 不返回推理文本 | — |
st-2.1-turbo | thinking_enabled | false |
st-2.1-pro | thinking_enabled | false |
st-2.0-mini | thinking_enabled | false |
以 Chat Completions 为基准。推理内容从 reasoning_content 读取,最终答案从 content 读取。对无法停用的版本不传递停用选项。
请求参数
| 参数 | 必填 | 类型 | 说明 |
|---|---|---|---|
model | 必填 | String | 各版本选项表中的模型 ID |
messages | 必填 | Array | Chat Completions / Messages 的对话输入 |
input | 必填 | String / Array | Responses 的输入。替代 messages 使用 |
max_tokens | 可选 | Integer | Chat Completions / Messages 的生成上限。在 Messages 中为必填 |
max_output_tokens | 可选 | Integer | Responses 的生成上限 |
stream | 可选 | Boolean | true:SSE / false:JSON |
请求示例
Chat Completions
json
{
"model": "st-2.1-pro",
"messages": [
{
"role": "user",
"content": "Reply with exactly OK and nothing else."
}
],
"max_tokens": 2048,
"stream": false,
"reasoning_effort": "low"
}响应
json
{
"id": "01a0de40-f4c7-718f-b783-0ff8d844ecd3",
"object": "chat.completion",
"model": "doubao-seed-2-1-pro-260628",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "OK",
"reasoning_content": "\nGot it,Content will be written as required.\n"
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 56,
"prompt_tokens_details": {
"audio_tokens": 0,
"cached_tokens": 0
},
"prompt_cached_tokens_details": {
"audio_tokens": 0
},
"completion_tokens": 25,
"completion_tokens_details": {
"accepted_prediction_tokens": 0,
"audio_tokens": 0,
"reasoning_tokens": 24,
"rejected_prediction_tokens": 0
},
"total_tokens": 81
}
}Responses
json
{
"model": "st-evolving",
"input": "Reply with exactly OK and nothing else.",
"max_output_tokens": 512,
"stream": false
}响应
json
{
"id": "resp_021790434702899d58e3edad71566bed3cb03770f22004fdcafa8",
"object": "response",
"model": "doubao-seed-evolving",
"status": "completed",
"output": [
{
"id": "rs_02179043470320000000000000000000000ffffac15109049bfd5",
"type": "reasoning",
"summary": [
{
"type": "summary_text",
"text": "We need obey user says exactly OK and nothing else. \n\nConflicting requirements between the developer and user have been found, and the exact user-specified \"OK\" will be output without markdown."
}
],
"status": "completed",
"encrypted_content": "djFq21LcuC8TJbMv6ktgbFidTtXlsGSviuQwPZD2htygvafMpYDXfKJMtIqPif6FPKUcXFBVTI9arUt64rhOPJ8Jx6fzdwwpxqsMov5In3488e2cpkkbm4NpPU8DvZg/JjGDw0BFionPsDAc2ylVhLhv6OH6fQrhMRPL3z7PN+Ew8wfzLDKX5qSOGHDsGE5Dw2SsH2PAi6pf8hIHHPQKzWxvUkeqSpoKQOpWeb9XJMj4oE3wFQzLmbym1k+guJtAIZDDFNuT0pGobmBDnX/u6rw2uVXoq4V/fOQnmHM3weSnY9mjt8pacfRMAqEvQzNULxvdXnfODxDY9Z4xOgpz5E8t9qeZ0G4uVeR3BVp9xvMK8mZvTx07Zu/p+AGVBU1DUdVXboiMXWMWHsrb6M8+EpU5kYqEyTpAg94bpOAgR6zK40s="
},
{
"type": "message",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "OK"
}
],
"status": "completed",
"id": "msg_02179043470547100000000000000000000ffffac151090e43667"
}
],
"usage": {
"input_tokens": 54,
"output_tokens": 63,
"total_tokens": 117,
"input_tokens_details": {
"cached_tokens": 0
},
"output_tokens_details": {
"reasoning_tokens": 62
}
}
}Messages
json
{
"model": "st-evolving",
"messages": [
{
"role": "user",
"content": "Reply with exactly OK and nothing else."
}
],
"max_tokens": 512,
"stream": false
}响应
json
{
"id": "01a0de35-0701-76af-97a6-0d541d743ca5",
"model": "doubao-seed-evolving",
"type": "message",
"role": "assistant",
"content": [
{
"text": "OK",
"type": "text"
}
],
"stop_reason": "end_turn",
"usage": {
"input_tokens": 54,
"output_tokens": 271
}
}特殊设置
st-2.0-mini、st-2.1-pro、st-2.1-turbo、st-character、st-evolving 是请求 model 中使用的标识符。图片输入通过 st-2.0-mini 和 st-2.1-pro 消息的 image_url Part 传入。
推理启用由 thinking_enabled 指定,强度由 reasoning_effort 指定。各模型允许的设置遵循下表。推理内容与最终答案通过 reasoning_content 与 content 区分。