LV
LLMversus
Anthropic

Claude Opus 4

Complete specs, pricing, and benchmark data for Claude Opus 4 by Anthropic. Last verified 2026-04-03.

VisionMultimodalJSON ModeFunctionsStreaming
Pricing

Input / 1M tokens

$15.00

Output / 1M tokens

$75.00

Cached Input / 1M

$1.50

Context & Output

Context Window

200K

Max Output

32,000

TTFT

500ms

Speed

50 tok/s

Benchmarks

Arena ELO

1330

Coding ELO

1360

Reasoning ELO

1340

HumanEval

95.2

MMLU

91.5

MATH

85.4

GPQA

74.8

Price History (Input $/M tokens)

Strengths
  • +Top-tier coding and reasoning
  • +Excellent agentic capabilities
  • +Strong instruction following
  • +200K context window
Limitations
  • -Most expensive model available
  • -Slower than Sonnet and Haiku
  • -Overkill for simple tasks

Best For

CodingAnalysisAgentsComplex Reasoning

Compare Claude Opus 4 with...

vs o4-minivs Gemini 2.5 Provs DeepSeek R1vs o3-minivs Grok 3vs GPT-4.1vs Llama 4 Maverickvs Claude Sonnet 4vs DeepSeek V3vs Gemini 2.0 Flashvs GPT-4ovs Qwen 2.5 Max
Official Pricing Page →