Claude Opus 4

by Anthropic

Claude Opus 4 via Vertex AI (US region)

VisionToolsStructured output
Context window
200K
Max output
32K
Input price
$15.00 /1M
Output price
$75.00 /1M

Benchmarks

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

Global rank#3 of 505 LLMs
TierFrontier
Output speed54 tok/s
First token22.79s
Intelligence Index57.3
Coding Index52.5
GPQA Diamond
91%
Humanity's Last Exam
40%
SciCode
55%
IFBench
59%
Long-context reasoning
70%
Terminal-Bench Hard
52%
τ²-Bench Telecom
89%

Available routes

The same Claude Opus 4 runs on 1 route through the Opper gateway. Each route has its own data-handling posture.

ProviderRegionZero data retentionTrainingLoggingContractInputOutput
Google CloudUSOpt-inNo
Abuse monitoring. Partner-model coverage requires written verification.
PAYG$15.00$75.00

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 by Anthropic — pricing, benchmarks, hosting routes | Opper AI