Claude Sonnet 4.6

silvamux/claude-sonnet-4-6

Claude Sonnet 4.6 is a balanced model for code comprehension and editing, complex text analysis and tool-driven tasks — built for bringing agentic capability into everyday engineering and 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 contextInputOutputCache readCache write
-$5 / 1M tokens$25 / 1M tokens$0.5 / 1M tokens$6.25 / 1M tokens

Capabilities

Claude Sonnet 4.6 scored 72 overall, performing well — a balanced everyday workhorse. It stands out in general knowledge (85%), information retrieval / RAG (83%) and text comprehension (80%), reliably answering knowledge questions and digesting documents for enterprise knowledge bases and customer support. Comparatively, code generation (58%) is weak; serious coding work should go to stronger models. For day-to-day knowledge and text tasks it is a dependable pick.

Overall
72/ 100良好
HighlightsGeneral Knowledge 85%Information Retrieval / RAG 83% · Text Comprehension 80%
Best forEnterprise Knowledge Q&A / Content Moderation & Risk Control / Customer SupportScenario fit 75%
Relative weaknessCode Generation58%

Advanced Capabilities

8 items
Agent Collaboration67%

18 questions · Mixed

Code Generation58%

12 questions · Objective

Code Comprehension & Debugging73%

6 questions · Mixed

Creative Writing66%

22 questions · Subjective

Information Retrieval / RAG83%

9 questions · Mixed

Long-Context Handling68%

16 questions · Subjective

Math & Science Reasoning72%

14 questions · Objective

Multilingual Capability72%

11 questions · Mixed

General Foundations

3 items
General Knowledge85%

10 questions · Mixed

Text Comprehension80%

23 questions · Subjective

Logical Reasoning73%

16 questions · Mixed

Safety & Compliance

2 items
Hallucination Control79%

15 questions · Subjective

Instruction Following63%

18 questions · Subjective

Performance

Claude Sonnet 4.6

claude-sonnet-4-6@260909
Last 24 hours · 105,744 requests
First token · TTFT · P50
1489ms
P95 1616 ms
Output speed · TPS · P50
34tok/s
P95 98 tok/s
Full response · E2E · P50
6.09s
P95 6.24 s
Request success rate
97.56%
103,163 completed requests
24-hour availability
24 hours ago12 hours agoNow

Claude Sonnet 4.6 example code and API

Proclaude-sonnet-4-6@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-sonnet-4-6@260909",
    "messages": [{"role": "user", "content": "Hello, please introduce yourself"}]
  }'