Anthropic: Claude Sonnet 4.6

anthropic/claude-sonnet-4.6

Claude Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation.

by Anthropic

Recent activity on Claude Sonnet 4.6

Tokens processed per day

Throughput

Providers	Min (tokens/s)	Max (tokens/s)	Avg (tokens/s)
Amazon Bedrock	27.57	41.19	35.19
Anthropic	37.61	55.09	47.53
Google Vertex	10.98	76.75	35.04

First Token Latency

Providers	Min (ms)	Max (ms)	Avg (ms)
Amazon Bedrock	2190	4128	2956.04
Anthropic	3010	3952	3382.86
Google Vertex	1032	2194	1425.00

Uptime stats for Claude Sonnet 4.6

Uptime	Providers
100.00%	Amazon Bedrock
100.00%	Anthropic
100.00%	Google Vertex

Pricing

Item	Price
Input	$ 3/ M tokens
Output	$ 15/ M tokens
Cache read	$ 0.3/ M tokens
Cache write (5m)	$ 3.75/ M tokens
Cache write (1h)	$ 6/ M tokens
Web search	$ 0.01/ counts

Model limitation

Context	Max output
1000.00K	64.00K

Sample code and API for Claude Sonnet 4.6

ZenMux normalizes requests and responses across providers for you.

from openai import OpenAI

client = OpenAI(
  base_url="https://zenmux.ai/api/v1",
  api_key="<ZENMUX_API_KEY>",
)

# Chat Completion
completion = client.chat.completions.create(
  model="anthropic/claude-sonnet-4.6",
  messages=[
    {
      "role": "user",
      "content": "What is the meaning of life?"
    }
  ]
)
print(completion.choices[0].message.content)

# Responses API
responses = client.responses.create(
  model="anthropic/claude-sonnet-4.6",
  input="What is the meaning of life?"
)
print(responses)