Publish time
2026/6/28Model Series
豆包seedInput type
Output type
Input Price
¥6 / 1M tokensOutput Price
¥30 / 1M tokensCache Write Price
¥7.5 / 1M tokensCache Read Price
¥1.2 / 1M tokensContext Window
256,000Max Output Length
256,000Seed 旗舰版 Coding & Agent 模型,视觉理解能力再次提升。 适合高复杂度任务探索,例如复杂 Coding、长链路 Agent、多步骤工程交付等场景。 适合高价值生产任务,例如需要更强的需求理解、长期规划、工具调用闭环和多模态推理能力的任务。 适合真实且要求稳定的生产场景。
Zhinao API routes requests to the best-fit provider and automatically fails over to the one with highest availability.
TTFT
21.84s
Throughput
30.93tps
Uptime
100.00%
Provider Model
nc/bytedance/doubao-seed-2-1-pro-260628
Supported Parameters
Recent Uptime
Reasoning
Toggleable
Supported Response Formats
Total Context
256,000
Max Output
256,000
Input Price
¥5.4 / 1M tokens
Output Price
¥27 / 1M tokens
Cache Write
¥6.75 / 1M tokens
Cache Read
¥1.08 / 1M tokens
TTFT
6.69s
Throughput
37.56tps
Uptime
100.00%
Provider Model
volcengine/bytedance/doubao-seed-2-1-pro
Supported Parameters
Recent Uptime
Reasoning
Toggleable
Supported Response Formats
Total Context
256,000
Max Output
256,000
Input Price
¥6 / 1M tokens
Output Price
¥30 / 1M tokens
Cache Write
¥7.5 / 1M tokens
Cache Read
¥1.2 / 1M tokens
Compare different providers across Zhinao API
40.37 tok/s
18.00 s
Uptime for bytedance/doubao-seed-2-1-pro across all providers
Zhinao API normalizes requests and responses across providers for you
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.360.cn/v1",
apiKey: process.env.ZHINAO_API_KEY,
});
const response = await client.chat.completions.create({
model: "bytedance/doubao-seed-2-1-pro",
messages: [
{ role: "user", content: "Hello, how are you?" }
],
temperature: 0.7,
max_tokens: 1000,
});
console.log(response.choices[0].message.content);