text
Claude Opus 4.5
silvamux/
claude-opus-4-5Claude Opus 4.5 is Anthropic's model oriented to language and content work, with standout multilingual capability and fluent writing — suited to translation, marketing copy and knowledge-base content.
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 4.5 scored 82 overall, performing well — a language-and-content specialist. It stands out in multilingual capability (93%), general knowledge (90%) and creative writing (90%), producing polished multilingual content with strong factual grounding, which makes it a strong pick for localization, marketing copy and knowledge-base writing. Comparatively, code generation (67%) is moderate; heavy engineering work is not its focus. Polished multilingual content is where it clearly wins.
82/ 100
Advanced Capabilities
8 itemsAgent Collaboration79%
18 questions · Mixed
Code Generation67%
12 questions · Objective
Code Comprehension & Debugging75%
6 questions · Mixed
Creative Writing90%
22 questions · Subjective
Information Retrieval / RAG86%
9 questions · Mixed
Long-Context Handling86%
16 questions · Subjective
Math & Science Reasoning83%
14 questions · Objective
Multilingual Capability93%
11 questions · Subjective
General Foundations
3 itemsGeneral Knowledge90%
10 questions · Mixed
Text Comprehension76%
23 questions · Mixed
Logical Reasoning70%
16 questions · Mixed
Safety & Compliance
2 itemsHallucination Control88%
15 questions · Subjective
Instruction Following78%
18 questions · Subjective
Performance
Claude Opus 4.5
claude-opus-4-5@snapLast 24 hours · 28,579 requests
- First token · TTFT · P50
- 2484ms P95 2494 ms
- Output speed · TPS · P50
- 31tok/s P95 72 tok/s
- Full response · E2E · P50
- 7.79s P95 8.00 s
- Request success rate
- 97.11% 27,754 completed requests
24-hour availability
24 hours ago12 hours agoNow
Claude Opus 4.5 example code and API
Pro
claude-opus-4-5@snap/api/v0/chat/completions/api/v1/chat/completions/api/anthropic/v1/messagescurl https://silvamux.io/api/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "claude-opus-4-5@snap",
"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-4-5@snap",
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-4-5@snap\",\"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-4-5@snap',
messages: [{ role: 'user', content: 'Hello, please introduce yourself' }],
})
console.log(response.choices[0].message.content)