GPT-5.6 is here 🎉 20% off all GPT 🎉 All July 🔥Learn more
Claude

Anthropic: Claude Sonnet 4.6

Chat
anthropic/claude-sonnet-4.6

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.

Context Window
1M
Max Output Tokens
128K
Released
2026-02-17
Capabilities
VisionFunction CallingReasoningPrompt CachingPDF Input
Available Providers
AzureAzureBedrockBedrock
Supported Protocols
OpenAIopenaiAnthropicanthropic

Providers

BedrockBedrock
Input Tokens
$3/M
Output Tokens
$15/M
Cache Read
$0.3/M
Cache Write (5 min)
$3.75/M
Cache Write (1 hour)
$6/M
Web Search
$0.015/R
Protocols
OpenAIopenai/v1/chat/completions/v1/responses
Anthropicanthropic
AzureAzure
Input Tokens
$3/M
Output Tokens
$15/M
Cache Read
$0.3/M
Cache Write (5 min)
$3.75/M
Cache Write (1 hour)
$6/M
Web Search
$0.015/R
Protocols
Anthropicanthropic

Sign in to try Anthropic: Claude Sonnet 4.6

Chat with this model right here.

Conversations live only in this page and are never stored.

Conversations are not saved — leaving or refreshing this page clears them.

Code Examples

import anthropic
client = anthropic.Anthropic(
base_url="https://api.ofox.io/anthropic",
api_key="YOUR_OFOX_API_KEY",
)
message = client.messages.create(
model="anthropic/claude-sonnet-4.6",
max_tokens=1024,
messages=[
{"role": "user", "content": "Hello!"}
],
)
print(message.content[0].text)

Uptime & Status

Benchmarks

LMArenaEvaluated as claude-sonnet-4-6

Anthropic: Claude Sonnet 4.6 scores 1472 in the Overall category of the LMArena text leaderboard (style control), ranking #26 of 374 models based on 53,682 human preference votes (updated 2026-07-12).

Benchmark scores for claude-sonnet-4-6 on LMArena
CategoryArena Score95% CIRankVotes
Overall147214681476#26 of 37453,682
Hard Prompts150414991509#13 of 37434,387
Coding152715211534#10 of 36914,752
Math146414531476#34 of 3622,955
Creative Writing145014421457#22 of 3728,815
Instruction Following147814721484#12 of 37417,328
Chinese150614931519#28 of 3442,624

Source: LMArena · CC BY 4.0 · Updated 2026-07-12 · Methodology · Ranks compare models within each category of the LMArena text leaderboard (style control). Scores come from third-party human preference evaluations, not from OFOX.

Frequently Asked Questions

Anthropic: Claude Sonnet 4.6 on Ofox.ai costs $3/M per million input tokens and $15/M per million output tokens. Pay-as-you-go, no monthly fees.