Publish time
2026/6/28Model Series
豆包seedInput type
Output type
Input Price
¥3 / 1M tokensOutput Price
¥15 / 1M tokensCache Write Price
¥3.75 / 1M tokensCache Read Price
¥0.6 / 1M tokensContext Window
256,000Max Output Length
256,000效果与成本均衡,全面升级编程、智能体与多模态能力。 适合规模化生产场景,例如需要稳定承接大量线上调用的 Coding、Agent 和多模态理解任务。 适合标准化业务流程的大规模落地,与 Pro 版本支持的能力一样。
Zhinao API routes requests to the best-fit provider and automatically fails over to the one with highest availability.
TTFT
12.42s
Throughput
45.04tps
Uptime
100.00%
Provider Model
nc/bytedance/doubao-seed-2-1-turbo-260628
Supported Parameters
Recent Uptime
Reasoning
Toggleable
Supported Response Formats
Total Context
256,000
Max Output
256,000
Input Price
¥2.7 / 1M tokens
Output Price
¥13.5 / 1M tokens
Cache Write
¥3.375 / 1M tokens
Cache Read
¥0.54 / 1M tokens
TTFT
2.65s
Throughput
47.21tps
Uptime
100.00%
Provider Model
volcengine/bytedance/doubao-seed-2-1-turbo
Supported Parameters
Recent Uptime
Reasoning
Toggleable
Supported Response Formats
Total Context
256,000
Max Output
256,000
Input Price
¥3 / 1M tokens
Output Price
¥15 / 1M tokens
Cache Write
¥3.75 / 1M tokens
Cache Read
¥0.6 / 1M tokens
Compare different providers across Zhinao API
49.45 tok/s
9.78 s
Uptime for bytedance/doubao-seed-2-1-turbo 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-turbo",
messages: [
{ role: "user", content: "Hello, how are you?" }
],
temperature: 0.7,
max_tokens: 1000,
});
console.log(response.choices[0].message.content);