Claude Opus 4.5
Most capable Claude model with extended thinking
VisionToolsStructured outputFiles
Context window
200K
Max output
64K
Input price
$5.00 /1M
Output price
$25.00 /1M
Benchmarks
Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.
Intelligence Index43.1
Coding Index42.9
Math Index62.7
MMLU-Pro
89%
GPQA Diamond
81%
Humanity's Last Exam
13%
LiveCodeBench
74%
SciCode
47%
AIME 2025
63%
IFBench
43%
Long-context reasoning
65%
Terminal-Bench Hard
41%
τ²-Bench Telecom
86%
See full leaderboard →Benchmarks via Artificial Analysis · View on AA
Available routes
The same Claude Opus 4.5 runs on 4 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 | $5.00 | $25.00 |
| AWS Bedrock | EU | Default | No | None | PAYG | $5.00 | $25.00 |
| Azure OpenAI | EU | Opt-in | No | Up to 30 days for abuse monitoring | EA/MCA-E | $5.00 | $25.00 |
| Google Cloud | US | Opt-in | No | Abuse monitoring. Partner-model coverage requires written verification. | PAYG | $5.00 | $25.00 |
Human review: Abuse-flagged only