modelgrep
A

Anthropic: Claude Opus 4.5

anthropic/claude-opus-4.5

29th smartest of 180ReasoningToolsJSONVision
Use via OpenRouter ↗
Intelligence
43.1
29th of 180
Design Elo
1297
Game Dev
Speed
51
172nd fastest
Latency
802ms
first token
Input price
$5.00
278th cheapest
Context
200K
64K max out

How it compares

Smarter than84%
of all ranked models
Faster than44%
of all ranked models
Cheaper than7%
of all ranked models

Overview

Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...

Benchmarks

independent · via OpenRouter
Artificial Analysis80th percentile
Intelligence Index
43.1
Coding Index
42.9
Agentic Index
59.2
GPQA Diamond
81%
Humanity's Last Exam
13%
SciCode
47%
Tau²-Bench (agentic)
86%
Design Arena · Elo16,000 tournaments
Game Dev
1297
UI Component
1295
3D
1293
codecategories
1293
Website
1292
Data Viz
1288
mobileapps
1248
webapps
1236
fullstack
1235
svg
1234
asciiart
1227
androidnative
1196

Providers & pricing (5)

ProviderIn $/MOut $/MUptime
Amazon Bedrock$5.00$25.00
Anthropic$5.00$25.00100%
Amazon Bedrock$5.00$25.0099.9%
Google$5.00$25.00100%
Anthropic$5.00$25.00

Specifications

Context window200K
Max output64K
Knowledge cutoff
Input modalitiesfile, image, text
Output modalitiestext
Prompt caching
Cache read price$0.500/M
ModeratedYes

Claude Opus 4.5 FAQ

How much does Claude Opus 4.5 cost?

Claude Opus 4.5 costs $5.00 per million input tokens and $25.00 per million output tokens via OpenRouter, making it 278th cheapest of 298 paid models.

How smart is Claude Opus 4.5?

Claude Opus 4.5 scores 43.1 on the Artificial Analysis Intelligence Index, ranking 29th of 180 benchmarked models, with a GPQA Diamond score of 81%.

How fast is Claude Opus 4.5?

Claude Opus 4.5 generates around 51 tokens per second with 802ms time-to-first-token (p50), the 172nd fastest tracked model.

What is Claude Opus 4.5's context window?

Claude Opus 4.5 supports a 200K-token context window and can output up to 64K tokens. It accepts file, image, text input.

Compare head-to-head