text·image
silvamux/
doubao-seed-2.0-codeDoubao Seed 2.0 Code的主要优势是文本理解与信息检索/RAG,并支持图像信息输入。在文档分析、信息抽取与复杂语义理解中,它能够承担信息理解、分析和结果生成等关键环节。
Pricing
Tiers are determined by the input context length of each request; Tune and Pro share the same tiered prices.
| Input context | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| ≤ 32K tokens | ¥3.2 | ¥16 | ¥0.64 | ¥3.2 |
| ≤ 128K tokens | ¥4.8 | ¥24 | ¥0.96 | ¥4.8 |
| > 128K tokens | ¥9.6 | ¥48 | ¥1.92 | ¥9.6 |
Capabilities
Doubao Seed 2.0 Code在本轮能力评测中综合得分78,整体表现良好。其文本理解(97%)和信息检索 / RAG(92%)表现突出,能够分析文档语义、提取关键信息并处理复杂问答,并从知识库和多来源资料中定位信息、组织证据并生成有依据的回答。对软件开发者和工程团队而言,它适合用于代码编写、代码库理解、重构调试等研发场景,解决在复杂代码任务中兼顾生成结果与上下文理解;代码生成(90%)也为相关任务提供补充。它的主要限制在于,智能体协同(45%)相对较弱,在需要多步骤自主规划、连续工具调用或跨智能体协作的任务中,建议增加人工复核或专项验证。
78/ 100
专项进阶能力
8 items智能体协同45%
7 questions · 主/客观混合
代码生成90%
10 questions · 客观
代码理解与调试73%
12 questions · 主/客观混合
创意写作76%
17 questions · 主观
信息检索 / RAG92%
13 questions · 主/客观混合
长文本处理67%
3 questions · 主观
数学与科学推理86%
14 questions · 客观
多语言能力83%
10 questions · 主/客观混合
通用基础能力
3 items通识知识76%
15 questions · 主/客观混合
文本理解97%
5 questions · 主观
逻辑推理74%
20 questions · 主/客观混合
安全与合规能力
2 items幻觉控制70%
9 questions · 主观
指令遵循79%
14 questions · 主观
Performance
Doubao Seed 2.0 Code
doubao-seed-2.0-code- 延迟
- 30.65s
- 吞吐量
- 1.76Ktokens/min
- 可用率
- 98.66%
Availability
98.66%- 完成率
- 99%
- 缓存命中率
- 动态变化
- 累计评测耗时
- 13558.2s
- Token 消耗
- 398,164tokens
- 平均请求次数
- 1.0次
- TPM
- 1,762tokens/min
- QPM
- 0.7req/min
Doubao Seed 2.0 Code example code and API
Pro
doubao-seed-2.0-code/api/v0/chat/completions/api/v3/chat/completionscurl https://www.silvamux.com/api/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "doubao-seed-2.0-code",
"messages": [{"role": "user", "content": "Hello, please introduce yourself"}]
}'# pip install openai
from openai import OpenAI
client = OpenAI(
base_url="https://www.silvamux.com/api/v1",
api_key="YOUR_API_KEY",
)
response = client.chat.completions.create(
model="doubao-seed-2.0-code",
messages=[
{"role": "user", "content": "Hello, please introduce yourself"}
],
)
print(response.choices[0].message.content)// Gradle: implementation(__HL_SLOT_0__)
import okhttp3.*;
OkHttpClient client = new OkHttpClient();
MediaType json = MediaType.get("application/json");
String payload = "{\"model\":\"doubao-seed-2.0-code\",\"messages\":[{\"role\":\"user\",\"content\":\"Hello, please introduce yourself\"}]}";
Request request = new Request.Builder()
.url("https://www.silvamux.com/api/v1/chat/completions")
.header("Authorization", "Bearer YOUR_API_KEY")
.post(RequestBody.create(payload, json))
.build();
try (Response response = client.newCall(request).execute()) {
System.out.println(response.body().string());
}// npm install openai
import OpenAI from 'openai'
const client = new OpenAI({
baseURL: 'https://www.silvamux.com/api/v1',
apiKey: 'YOUR_API_KEY',
})
const response = await client.chat.completions.create({
model: 'doubao-seed-2.0-code',
messages: [{ role: 'user', content: 'Hello, please introduce yourself' }],
})
console.log(response.choices[0].message.content)