AI Index

Claude Opus 4

Language Anthropic Partly verified Retired Shut down Jun 15, 2026 Released May 22, 2025
Model ID
Compare with… →
Context
200K
32K max output
Input price
—
Not listed
Output price
—
Not listed
Epoch Capabilities Index
142.7
#77 of 105 listed
LMArena Text
1,414
#88 of 149 listed

Where to run it

2 offerings · prices as listed
MeterTierPrice
Claude API Official Retired Global · USD claude-opus-4-20250514
InputStandard past price, from the vendor’s page archived Jun 11, 2026$15.00 / 1M tokens
Batch past price, from the vendor’s page archived Jun 11, 2026$7.50 / 1M tokens
OutputStandard past price, from the vendor’s page archived Jun 11, 2026$75.00 / 1M tokens
Batch past price, from the vendor’s page archived Jun 11, 2026$37.50 / 1M tokens
Cache readStandard past price, from the vendor’s page archived Jun 11, 2026$1.50 / 1M tokens
Cache write5-minute cache past price, from the vendor’s page archived Jun 11, 2026$18.75 / 1M tokens
1-hour cache past price, from the vendor’s page archived Jun 11, 2026$30.00 / 1M tokens
Amazon Bedrock us-east-1 · USD Claude Opus 4
InputStandard $15.00 / 1M tokens
Batch $7.50 / 1M tokens
OutputStandard $75.00 / 1M tokens
Batch $37.50 / 1M tokens
Cache readStandard $1.50 / 1M tokens
Cache write5-minute cache $18.75 / 1M tokens

Changes

All changes →
  1. 4 new prices on Claude API Cache write (5-minute cache) $18.75 · Cache write (1-hour cache) $30.00 · Input (Batch) $7.50 · Output (Batch) $37.50
  2. 4 new prices on Claude API Cache write (5-minute cache) $18.75 · Cache write (1-hour cache) $30.00 · Input (Batch) $7.50 · Output (Batch) $37.50

Cited scores

From third-party leaderboards, not measured by us
  • Epoch Capabilities Index 142.7

    #77 of 105 listed models · CI 140.2–144.2

  • LMArena Text 1,414

    #88 of 149 listed models · CI 1,410–1,418 · 42,792 votes

  • Epoch AI · GPQA Diamond 76.3%

    #75 of 128 listed models · 16K thinking budget · ±3.03

    Also listed: claude-opus-4-20250514 69.2%

  • Epoch AI · SWE-bench Verified 70.7%

    #22 of 30 listed models · ±2.07

  • LMArena Text · Chinese 1,441

    #90 of 149 listed models · CI 1,430–1,452 · 3,072 votes

  • LMArena Text · Coding 1,465

    #81 of 149 listed models · CI 1,458–1,472 · 7,790 votes

  • LMArena Vision 1,175

    #65 of 87 listed models · CI 1,162–1,188 · 2,177 votes

  • Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Oct 3, 2026
  • LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Oct 2, 2026
  • Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Oct 1, 2026
  • changes we made