Claude Opus 4.6

by Anthropic

Most intelligent Claude model for agents and coding

VisionToolsStructured outputFiles
Context window
1M
Max output
128K
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.

Global rank#37 of 505 LLMs
TierStrong
Output speed46 tok/s
First token1.49s
Intelligence Index46.5
Coding Index47.6
GPQA Diamond
84%
Humanity's Last Exam
19%
SciCode
46%
IFBench
45%
Long-context reasoning
58%
Terminal-Bench Hard
49%
τ²-Bench Telecom
85%

Available routes

The same Claude Opus 4.6 runs on 2 different routes through the Opper gateway. Each route has its own data-handling posture.

ProviderRegionZero data retentionTrainingLoggingContractInputOutput
AnthropicUSOpt-inNo (opt-in)
Abuse monitoring; default duration not in public docs (DPA needed).
Enterprise$5.00$25.00
AWS BedrockEUDefaultNo
None
PAYG$5.00$25.00

Human review: Abuse-flagged only

Other models from Anthropic

Start building with 300+ models

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

Get startedView Documentation
Claude Opus 4.6 by Anthropic — pricing, benchmarks, hosting routes | Opper AI