Next-generation coding and agent model with engineering-grade code delivery, long-horizon autonomy, and 256K multimodal understanding.
ByteDance文本生成256K 上下文发布日期 2026年7月13日Malaysia专有端点新Next-generation coding and agent model with engineering-grade code delivery, long-horizon autonomy, and 256K multimodal understanding.
也称为 Seed Turbo, ByteDance Seed 2.1 Turbo, Seed-2.1-Turbo, seed-2-1-turbo
seed-2-1-turbo/v1/chat/completionsPOST/v1/responsesPOST/v1/messagesPOST/v1beta/models/seed-2-1-turbo:generateContentbytedance/seed-2-1-turbodola-seed-2.1-turbodola-seed-2-1-turbo-260628来自 EmpirioLabs 目录的实时按量计费价格。只为实际用量付费，没有月度最低消费。
Seed 2.1 Turbo 提供 OpenAI 兼容的 Chat Completions API。用你的 EmpirioLabs API 密钥把任意 OpenAI SDK 指向 https://api.empiriolabs.ai/v1，并使用模型 ID seed-2-1-turbo。 在EmpirioLabs 控制台获取 API 密钥。
curl https://api.empiriolabs.ai/v1/chat/completions \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seed-2-1-turbo",
"messages": [
{"role": "user", "content": "Write a haiku about the ocean."}
]
}'from openai import OpenAI
client = OpenAI(
base_url="https://api.empiriolabs.ai/v1",
api_key="YOUR_EMPIRIOLABS_API_KEY",
)
response = client.chat.completions.create(
model="seed-2-1-turbo",
messages=[{"role": "user", "content": "Write a haiku about the ocean."}],
)
print(response.choices[0].message.content)EmpirioLabs 上 Seed 2.1 Turbo API 支持的请求参数。省略字段时使用默认值。
| 参数 | 类型 | 默认值 | 范围 / 值 | 描述 |
|---|---|---|---|---|
| max_tokens | number | 4096 | 1 到 65536 | Max output tokens |
| frequency_penalty | number | 0 | -2 到 2 | Penalty for repeated tokens. >0 reduces repetition, <0 encourages it. |
| presence_penalty | number | 0 | -2 到 2 | Penalty for new vs. seen tokens. >0 encourages new topics, <0 encourages staying on topic. |
| stop | string | - | - | Comma-separated stop sequences |
| enable_thinking | boolean | true | - | Enable deep thinking / reasoning mode. |
| reasoning_effort | enum | high | low, medium, high | Reasoning effort tier. Use enable_thinking=false to disable reasoning entirely. |
| enable_web_search | boolean | false | - | Enable web search: retrieves live web results and provides them to the model as additional context. |
| image_detail | enum | high | low, high, xhigh | Image visual quality tier for vision input. |
| video_fps | number | - | 0.2 到 5 | Frames per second extracted from video input. |
| response_format | enum | - | - | Constrain the output to JSON. Use JSON mode for any valid JSON object, or JSON schema to force output that matches a schema you provide. |
Per-token pricing is flat across the full 256K context, with no higher rate above 128K. Reasoning is on by default; set enable_thinking to false to answer directly without it.
在 EmpirioLabs，Seed 2.1 Turbo 按量计费：Input $0.63 per 1M prompt tokens; Output $3.13 per 1M generated tokens。本页的实时价格表始终与 API 的实际计费一致。
Seed 2.1 Turbo 支持 256K token 的上下文窗口，每次响应最多 65,536 个输出 token。
兼容。Seed 2.1 Turbo 提供 OpenAI 兼容的 Chat Completions API，现有 OpenAI SDK 只需把 base_url 指向 https://api.empiriolabs.ai/v1 并把模型 ID 设为 seed-2-1-turbo 即可使用。
可以。EmpirioLabs Playground在浏览器中以与 API 相同的参数运行 Seed 2.1 Turbo，你可以在写代码之前先测试提示词。
创建 EmpirioLabs 账户，然后在控制台的 API Keys生成密钥。计费使用按量付费的额度，只为实际发出的请求付费。
