Claude Opus 4.8

Name: Claude Opus 4.8 API
Brand: Anthropic
SKU: claude-opus-4-8

silvamux/claude-opus-4-8

Claude Opus 4.8 targets demanding software engineering and professional knowledge tasks — it reads code, calls tools and drives plans forward over long workflows, fitting large development projects and in-depth research.

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 4.8 scored 79 overall, performing well — a model oriented toward knowledge accuracy and reasoning. It stands out in general knowledge (92%), math and science reasoning (89%) and hallucination control (88%), keeping factual errors in check while reasoning through professional problems, which makes it reliable for customer support, e-commerce copywriting and scriptwriting. Comparatively, code generation (67%) is moderate; complex coding tasks are better delegated elsewhere. Value concentrates in knowledge-heavy, accuracy-sensitive work.

Overall

79/ 100良好

HighlightsGeneral Knowledge 92%Math & Science Reasoning 89% · Hallucination Control 88%

Best forCustomer Support / E-commerce Copywriting / ScriptwritingScenario fit 82%

Relative weaknessCode Generation67%

Advanced Capabilities

8 items

Agent Collaboration76%

18 questions · Mixed

Code Generation67%

12 questions · Objective

Code Comprehension & Debugging69%

6 questions · Mixed

Creative Writing81%

22 questions · Subjective

Information Retrieval / RAG72%

9 questions · Mixed

Long-Context Handling87%

16 questions · Subjective

Math & Science Reasoning89%

14 questions · Mixed

Multilingual Capability75%

11 questions · Mixed

General Foundations

3 items

General Knowledge92%

10 questions · Mixed

Text Comprehension75%

23 questions · Subjective

Logical Reasoning74%

16 questions · Mixed

Safety & Compliance

2 items

Hallucination Control88%

15 questions · Subjective

Instruction Following80%

18 questions · Subjective

Performance

Claude Opus 4.8

claude-opus-4-8@260909

Last 24 hours · 54,090 requests

First token · TTFT · P50: 1867ms
Output speed · TPS · P50: 90tok/s
Full response · E2E · P50: 6.40s
Request success rate: 97.02%

24-hour availability

24 hours ago12 hours agoNow

Claude Opus 4.8 example code and API

Proclaude-opus-4-8@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-4-8@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-4-8@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-4-8@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-4-8@260909',
  messages: [{ role: 'user', content: 'Hello, please introduce yourself' }],
})

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