modelgrep
A

Anthropic: Claude Opus 4

anthropic/claude-opus-4

ReasoningToolsVision
Use via OpenRouter ↗
Intelligence
Design Elo
1240
Game Dev
Speed
23
265th fastest
Latency
2.5s
first token
Input price
$15.00
289th cheapest
Context
200K
32K max out

How it compares

Faster than14%
of all ranked models
Cheaper than3%
of all ranked models

Overview

Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new benchmarks in...

Benchmarks

independent · via OpenRouter
Artificial Analysis
Coding Index
34.0
GPQA Diamond
80%
Humanity's Last Exam
12%
SciCode
40%
Tau²-Bench (agentic)
73%
Design Arena · Elo7,928 tournaments
Game Dev
1240
3D
1220
codecategories
1212
UI Component
1210
Website
1209
Data Viz
1189
svg
1184

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
Google$15.00$75.00100%

Specifications

Context window200K
Max output32K
Knowledge cutoffJan 2025
Input modalitiesimage, text, file
Output modalitiestext
Prompt caching
Cache read price$1.50/M
ModeratedNo

Claude Opus 4 FAQ

How much does Claude Opus 4 cost?

Claude Opus 4 costs $15.00 per million input tokens and $75.00 per million output tokens via OpenRouter, making it 289th cheapest of 298 paid models.

How fast is Claude Opus 4?

Claude Opus 4 generates around 23 tokens per second with 2.5s time-to-first-token (p50), the 265th fastest tracked model.

What is Claude Opus 4's context window?

Claude Opus 4 supports a 200K-token context window and can output up to 32K tokens. It accepts image, text, file input.

Compare head-to-head