Claude Sonnet 4.6

by Anthropic

Claude Sonnet 4.6 is Anthropic's most capable Sonnet model, a full upgrade across coding, computer use, long-context reasoning, agent planning, knowledge work, and design. Early-access developers often prefer it to the more advanced Opus 4.5, with performance frequently matching what previously required an Opus-class model. The model performs strongly on real-world, economically valuable office tasks. It reasons effectively over very long inputs, handling entire codebases, lengthy contracts, and dozens of research papers in a single request. Substantial improvements in computer-use automation let it interact with specialized tools and legacy systems using mouse clicks and keyboard input like a human operator. Sonnet 4.6 also shows improved resistance to prompt injection while maintaining safety standards comparable to other recent Claude models.

Key info

Input
Output
Features
Context window
1M
Max output
64K
Input price
$3.00 /1M
Output price
$15.00 /1M
  • EU residency available
  • US residency available
  • Zero data retention on pay-as-you-go
  • No training by default
  • GDPR DPA available

Available routes

Claude Sonnet 4.6 runs on 5 different routes through the Opper gateway. Compare residency, ZDR, and training posture at a glance β€” full data-handling detail per route below.

ProviderRegionZero data retentionTrainingInputOutput
AnthropicUSEnterpriseNo$3.00$15.00
AWS BedrockEUZero data retentionNo$3.30$16.50
AzureEUEnterpriseNo$3.00$15.00
Google CloudUSEnterpriseNo$3.00$15.00
Google CloudEUEnterpriseNo$3.30$16.50

Training posture across routes: No training on prompts by default.

Data handling per route

Each route hosting Claude Sonnet 4.6 has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Anthropic β€” United StatesπŸ‡ΊπŸ‡Έ

Zero data retention is available via Opper Enterprise contract. No training on customer data. US; SCCs; DPA available.

Zero data retention
Available via Opper Enterprise contract.
Training
No training on customer data.
Logging
Abuse monitoring
Third-party access
Provider may share with subprocessors / partners
GDPR DPA
DPA available
Transfer mechanism
SCCs

AWS Bedrock β€” SwedenπŸ‡ΈπŸ‡ͺ

Zero data retention is on by default on Pay-as-you-go β€” no action required. No training on customer data. EU; DPA available.

Zero data retention
On by default on Pay-as-you-go.
Training
No training on customer data.
Logging
None
Third-party access
None disclosed
GDPR DPA
DPA available
Transfer mechanism
Not applicable β€” data stays in EU

Azure β€” SwedenπŸ‡ΈπŸ‡ͺ

Zero data retention is available via Opper Enterprise contract. No training on customer data. EU; DPA available.

Zero data retention
Available via Opper Enterprise contract.
Training
No training on customer data.
Logging
Abuse monitoring (30-day retention)
Third-party access
None disclosed
GDPR DPA
DPA available
Transfer mechanism
Not applicable β€” data stays in EU

Google Cloud β€” United StatesπŸ‡ΊπŸ‡Έ

Zero data retention is available via Opper Enterprise contract. No training on customer data. US; SCCs; DPA available.

Zero data retention
Available via Opper Enterprise contract.
Training
No training on customer data.
Logging
Abuse monitoring
Third-party access
None disclosed
GDPR DPA
DPA available
Transfer mechanism
SCCs

Google Cloud β€” European UnionπŸ‡ͺπŸ‡Ί

Zero data retention is available via Opper Enterprise contract. No training on customer data. EU; DPA available.

Zero data retention
Available via Opper Enterprise contract.
Training
No training on customer data.
Logging
Abuse monitoring
Third-party access
None disclosed
GDPR DPA
DPA available
Transfer mechanism
Not applicable β€” data stays in EU

Benchmarks

Independent benchmark scores β€” composite indices for reasoning, coding, and math, plus individual eval scores where available.

Global rank#57 of 531 LLMs
TierStrong
Output speed49 tok/s
First token1.14s
Intelligence Index35.9
Coding Index46.4
Reasoning & knowledge
GPQA Diamond
80%
Humanity's Last Exam
13%
Long-context reasoning
58%
Coding
SciCode
47%
Agentic & tool use
Terminal-Bench Hard
46%
τ²-Bench Telecom
80%
Math & instruction following
IFBench
41%

Get started

Call Claude Sonnet 4.6 through the Opper gateway with one API key. Let your coding agent set it up, or call it directly β€” Opper is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.

Set it up with your agent

Copy this and paste it into your coding agent β€” Claude Code, Cursor, Codex, and more β€” and it'll wire up Opper for you.

Or call it directly

import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.OPPER_API_KEY,
baseURL: "https://api.opper.ai/v3/compat",
});
const completion = await client.chat.completions.create({
model: "anthropic/claude-sonnet-4-6",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Compare Claude Sonnet 4.6 with…

Side-by-side on privacy, EU hosting, pricing, and benchmarks.

Other models from Anthropic

Start building with 300+ models

One API key. Every major provider. Up and running in minutes.

Get startedView Documentation
Claude Sonnet 4.6 by Anthropic β€” pricing, benchmarks, ZDR, EU/US hosting | Opper AI