Claude Opus 4 — Anthropic | Modeldex

Claude Opus 4

Active75.7Strong

Anthropic's most capable model for complex reasoning and long-context work.

Updated 4 days agoStructured data from Modeldex catalog

VisionAgenticLong contextReasoningCode

Knowledge cutoff

Jan 31, 2025(1.2 years ago)

API release

May 22, 2025(11 months ago)

Intelligence Index

75.7/ 100

Strongweighted across 8 benchmarks

General knowledge: 82.5
Reasoning: 74.0
Math: 73.9
Coding: 72.5

Computed as the mean of per-category averages across MMLU, GPQA, SWE-bench, HumanEval, MATH, GSM8K, AIME, Aider Polyglot and more. See each benchmark for methodology.

Overview

Claude Opus 4 is Anthropic's flagship model, optimized for deep reasoning, coding, and extended agentic workflows. Supports 200k context, tool use, and structured outputs.

History

Claude Opus 4 became available via the Anthropic API on 2025-05-22.

Training & availability

Training data has a knowledge cutoff of 2025-01-31 — information about events after that date is unlikely to appear in the model's responses. Anthropic has not released the underlying model weights — access is via their hosted API only.

Capabilities

Context window: 200K tokens.
Max output: 64K tokens.
Input modalities: text, image.
Intelligence Index: 75.7/100.

Strongest categories: General knowledge (82), Reasoning (74), Math (74).

Recommended for: vision, agentic, long-context, reasoning, code.

Limitations

The knowledge cutoff is 14 months old — this model will not know about recent events, releases, or API changes.

Pricing

Input: $5.0000 per 1M tokens
Output: $25.0000 per 1M tokens

Use the cost calculator above to estimate monthly spend for your workload.

Quick start

Minimal example using the anthropic API. Copy, paste, replace the key.

from anthropic import Anthropic

client = Anthropic(api_key="sk-ant-...")
resp = client.messages.create(
    model="claude-opus-4",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Explain quantum computing in one sentence."}],
)
print(resp.content[0].text)

Cost calculator

Estimate your monthly bill. Presets are typical workload sizes.

Input tokens / month5.0M

@ $5/1M

Output tokens / month2.0M

@ $25/1M

Input cost

$25

5.0M × $5/1M

Output cost

$50

2.0M × $25/1M

Total / month

$75

$900 / year

Benchmarks

Benchmark	Score	Source
AIME 2024Math	48% accuracy	Third-party Artificial Analysis
GPQA DiamondReasoning	74% accuracy	Self-reported Anthropic model card
GSM8KMath	95.4% accuracy	Self-reported Anthropic model card

Integrations & tooling support

Tool calling: Supported
Structured outputs: Supported

Price vs quality

Overpriced

Mid-tier performance at frontier pricing.

Quality percentile: 44.5%
Effective price: $20/1M
Pricing breakdown: $5/1M in
$25/1M out

Community ratings

No ratings yet. Be the first to rate Claude Opus 4.