Claude Opus 5

Name: Claude Opus 5 API
Brand: Anthropic
SKU: claude-opus-5

silvamux/claude-opus-5

Claude Opus 5 is Anthropic's new-generation flagship, excelling at complex reasoning, engineering and professional knowledge tasks — built for demanding software projects, data analysis and deep knowledge work.

Supported modalities

text

Input price$5 / 1M tokensper 1M tokens

Output price$25 / 1M tokensper 1M tokens

Pricing

Tune and Pro share the same prices.

Input context	Input	Output	Cache read	Cache write
-	$5 / 1M tokens	$25 / 1M tokens	$0.5 / 1M tokens	$6.25 / 1M tokens

Capabilities

Claude Opus 5 scored 79 overall, performing well — Anthropic's new-generation flagship oriented to reasoning and engineering. It stands out in general knowledge (97%), code generation (92%) and math and science reasoning (89%), producing high-quality code alongside deep, accurate analysis, giving it an edge in development support and data analysis. Comparatively, information retrieval / RAG (58%) is weak; retrieval-grounded workflows need external support. Reasoning- and code-heavy tasks are where it performs best.

Overall

79/ 100良好

HighlightsGeneral Knowledge 97%Code Generation 92% · Math & Science Reasoning 89%

Best forCoding Assistance / Data Analysis / Customer SupportScenario fit 86%

Relative weaknessInformation Retrieval / RAG58%

Advanced Capabilities

8 items

Agent Collaboration81%

18 questions · Mixed

Code Generation92%

12 questions · Objective

Code Comprehension & Debugging80%

6 questions · Mixed

Creative Writing64%

22 questions · Mixed

Information Retrieval / RAG58%

9 questions · Mixed

Long-Context Handling71%

16 questions · Mixed

Math & Science Reasoning89%

14 questions · Mixed

Multilingual Capability86%

11 questions · Mixed

General Foundations

3 items

General Knowledge97%

10 questions · Mixed

Text Comprehension71%

23 questions · Mixed

Logical Reasoning66%

16 questions · Mixed

Safety & Compliance

2 items

Hallucination Control87%

15 questions · Mixed

Instruction Following81%

18 questions · Mixed

Performance

Claude Opus 5

claude-opus-5@260909

Last 24 hours · 14,774 requests

First token · TTFT · P50: 537ms
Output speed · TPS · P50: 73tok/s
Full response · E2E · P50: 3.22s
Request success rate: 98.28%

24-hour availability

24 hours ago12 hours agoNow

Claude Opus 5 example code and API

Proclaude-opus-5@260909

/api/v0/chat/completions/api/anthropic/v1/messages

UnifiedAnthropic

curl https://silvamux.io/api/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-5@260909",
    "messages": [{"role": "user", "content": "Hello, please introduce yourself"}]
  }'

# pip install openai
from openai import OpenAI

client = OpenAI(
    base_url="https://silvamux.io/api/v1",
    api_key="YOUR_API_KEY",
)

response = client.chat.completions.create(
    model="claude-opus-5@260909",
    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\":\"claude-opus-5@260909\",\"messages\":[{\"role\":\"user\",\"content\":\"Hello, please introduce yourself\"}]}";

Request request = new Request.Builder()
    .url("https://silvamux.io/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://silvamux.io/api/v1',
  apiKey: 'YOUR_API_KEY',
})

const response = await client.chat.completions.create({
  model: 'claude-opus-5@260909',
  messages: [{ role: 'user', content: 'Hello, please introduce yourself' }],
})

console.log(response.choices[0].message.content)