Claude Sonnet 4.6
Anthropic's balanced workhorse — strong reasoning at a fraction of Opus pricing.
VisionToolsStructured outputFiles
Context window
1M
Max output
64K
Input price
$3.00 /1M
Output price
$15.00 /1M
Benchmarks
Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.
Intelligence Index44.4
Coding Index46.4
GPQA Diamond
80%
Humanity's Last Exam
13%
SciCode
47%
IFBench
41%
Long-context reasoning
58%
Terminal-Bench Hard
46%
τ²-Bench Telecom
80%
See full leaderboard →Benchmarks via Artificial Analysis · View on AA
Available routes
The same Claude Sonnet 4.6 runs on 5 different routes through the Opper gateway. Each route has its own data-handling posture.
| Provider | Region | Zero data retention | Training | Logging | Contract | Input | Output |
|---|---|---|---|---|---|---|---|
| Anthropic | US | Opt-in | No (opt-in) | Abuse monitoring; default duration not in public docs (DPA needed). | Enterprise | $3.00 | $15.00 |
| AWS Bedrock | EU | Default | No | None | PAYG | $3.30 | $16.50 |
| Azure OpenAI | EU | Opt-in | No | Up to 30 days for abuse monitoring | EA/MCA-E | $3.00 | $15.00 |
| Google Cloud | EU | Opt-in | No | Abuse monitoring. Vertex ZDR doc excludes partner models — partner-specific terms apply, verify in writing. | PAYG | $3.00 | $15.00 |
| Google Cloud | EU | Opt-in | No | Abuse monitoring. Vertex ZDR doc excludes partner models — partner-specific terms apply, verify in writing. | PAYG | $3.30 | $16.50 |
Human review: Abuse-flagged only