Claude Fable 5.1
claude-fable-5-1Claude Fable 5.1 is Anthropic's updated language model, balancing professional knowledge, coding and analytical reasoning — suited to data analysis, content moderation and customer support.
Pricing
Tune and Pro share the same prices.
| Input context | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| - | $10 / 1M tokens | $50 / 1M tokens | $0.25 / 1M tokens | $12.5 / 1M tokens |
Capabilities
Claude Fable 5.1 scored 75 overall, performing well — a knowledge and analysis workhorse. It stands out in general knowledge (86%), code generation (84%) and math and science reasoning (81%), covering professional questions with dependable analysis, which serves data analysis, content moderation and support scenarios. Comparatively, agent collaboration (57%) is weak; multi-step tool orchestration is a stretch. Steady single-round knowledge and analysis work is where it fits.
Advanced Capabilities
8 items18 questions · Mixed
12 questions · Objective
6 questions · Mixed
22 questions · Subjective
9 questions · Mixed
16 questions · Subjective
14 questions · Mixed
11 questions · Mixed
General Foundations
3 items10 questions · Mixed
23 questions · Subjective
16 questions · Mixed
Safety & Compliance
2 items15 questions · Subjective
18 questions · Subjective
Performance
Claude Fable 5.1
claude-fable-5-1@snap- First token · TTFT · P50
- 880ms P95 1057 ms
- Output speed · TPS · P50
- 42tok/s P95 61 tok/s
- Full response · E2E · P50
- 9.30s P95 9.66 s
- Request success rate
- 97.53% 35,626 completed requests
Claude Fable 5.1 example code and API
claude-fable-5-1@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-fable-5-1@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-fable-5-1@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-fable-5-1@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-fable-5-1@snap',
messages: [{ role: 'user', content: 'Hello, please introduce yourself' }],
})
console.log(response.choices[0].message.content)