GoTry AI
EN 中文

Claude Opus 5

Language Anthropic Available Released Jul 24, 2026 Partly verified
Model ID
Compare with… →
Context
1M
128K max output
Input price
$5.00
per 1M tokens · Claude API
Output price
$25.00
per 1M tokens
Epoch Capabilities Index
162.7
#4 of 71 listed
LMArena Text
1,491
#9 of 79 listed

Where to run it

7 offerings · prices as listed
MeterTierPrice
Claude API Official Global · USD claude-opus-5
InputStandard $5.00 / 1M tokens
Batch $2.50 / 1M tokens
OutputStandard $25.00 / 1M tokens
Batch $12.50 / 1M tokens
Cache readStandard $0.50 / 1M tokens
Cache write5-minute cache $6.25 / 1M tokens
1-hour cache $10.00 / 1M tokens
Amazon Bedrock us-east-1 · USD Claude Opus 5
InputStandard $5.50 / 1M tokens
Batch $2.75 / 1M tokens
OutputStandard $27.50 / 1M tokens
Batch $13.75 / 1M tokens
Cache readStandard $0.55 / 1M tokens
Cache write5-minute cache $6.88 / 1M tokens
1-hour cache $11.00 / 1M tokens
Amazon Bedrock eu-central-1 · USD Claude Opus 5
InputStandard $5.50 / 1M tokens
Batch $2.75 / 1M tokens
OutputStandard $27.50 / 1M tokens
Batch $13.75 / 1M tokens
Cache readStandard $0.55 / 1M tokens
Cache write5-minute cache $6.88 / 1M tokens
1-hour cache $11.00 / 1M tokens
Amazon Bedrock ap-northeast-1 · USD Claude Opus 5
InputStandard $5.50 / 1M tokens
Batch $2.75 / 1M tokens
OutputStandard $27.50 / 1M tokens
Batch $13.75 / 1M tokens
Cache readStandard $0.55 / 1M tokens
Cache write5-minute cache $6.88 / 1M tokens
1-hour cache $11.00 / 1M tokens
Google Cloud Vertex AI Global · USD claude-opus-5
InputStandard $5.00 / 1M tokens
Batch $2.50 / 1M tokens
Prompts over 200K tokens $5.00 / 1M tokens
OutputStandard $25.00 / 1M tokens
Batch $12.50 / 1M tokens
Prompts over 200K tokens $25.00 / 1M tokens
Cache readStandard $0.50 / 1M tokens
Batch $0.25 / 1M tokens
Prompts over 200K tokens $0.50 / 1M tokens
Cache write5-minute cache $6.25 / 1M tokens
1-hour cache $10.00 / 1M tokens
5-minute cache · Batch $3.13 / 1M tokens
1-hour cache · Batch $5.00 / 1M tokens
Prompts over 200K tokens · 5-minute cache $6.25 / 1M tokens
Prompts over 200K tokens · 1-hour cache $10.00 / 1M tokens
Google Cloud Vertex AI us · USD Claude Opus 5
InputStandard $5.50 / 1M tokens
Batch $2.75 / 1M tokens
Prompts over 200K tokens $5.50 / 1M tokens
OutputStandard $27.50 / 1M tokens
Batch $13.75 / 1M tokens
Prompts over 200K tokens $27.50 / 1M tokens
Cache readStandard $0.55 / 1M tokens
Batch $0.28 / 1M tokens
Prompts over 200K tokens $0.55 / 1M tokens
Cache write5-minute cache $6.88 / 1M tokens
1-hour cache $11.00 / 1M tokens
5-minute cache · Batch $3.44 / 1M tokens
1-hour cache · Batch $5.50 / 1M tokens
Prompts over 200K tokens · 5-minute cache $6.88 / 1M tokens
Prompts over 200K tokens · 1-hour cache $11.00 / 1M tokens
Google Cloud Vertex AI eu · USD Claude Opus 5
InputStandard $5.50 / 1M tokens
Batch $2.75 / 1M tokens
Prompts over 200K tokens $5.50 / 1M tokens
OutputStandard $27.50 / 1M tokens
Batch $13.75 / 1M tokens
Prompts over 200K tokens $27.50 / 1M tokens
Cache readStandard $0.55 / 1M tokens
Batch $0.28 / 1M tokens
Prompts over 200K tokens $0.55 / 1M tokens
Cache write5-minute cache $6.88 / 1M tokens
1-hour cache $11.00 / 1M tokens
5-minute cache · Batch $3.44 / 1M tokens
1-hour cache · Batch $5.50 / 1M tokens
Prompts over 200K tokens · 5-minute cache $6.88 / 1M tokens
Prompts over 200K tokens · 1-hour cache $11.00 / 1M tokens

Changes

All changes →
  1. 3 new prices on Claude API Cache write (1-hour cache) $10.00 · Input (Batch) $2.50 · Output (Batch) $12.50

Vendor-reported scores

Published by Anthropic, under the conditions it states
BenchmarkSettingScore
SWE-bench Verifiedadaptive thinking, max effort, average of 5 trials96%
SWE-bench Proadaptive thinking, max effort, average of 5 trials79.2%
SWE-bench Multilingualadaptive thinking, max effort, average of 5 trials89.5%
SWE-bench Multimodaladaptive thinking, max effort, average of 5 trials59.4%
DeepSWE 1.1adaptive thinking, max effort68.8%
BrowseCompweb search, web fetch, programmatic tool calling, code execution; context compaction at 200k; max effort90.8%
Humanity's Last Examno tools, max effort56.3%
with web search, web fetch, programmatic tool calling, code execution; max effort64.7%

Cited scores

From third-party leaderboards, not measured by us
  • Epoch Capabilities Index 162.7

    #4 of 71 listed models · CI 160–166.5

    Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made

  • LMArena Text 1,491

    #9 of 79 listed models · high effort · CI 1,487–1,495 · 55,063 votes

    Also listed: max effort 1,488

    LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made

  • Epoch AI · FrontierMath Tiers 1–3 85.6%

    #7 of 56 listed models · max effort · ±2.08

    Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made

  • Epoch AI · GPQA Diamond 93.9%

    #8 of 64 listed models · max effort · ±1.48

    Also listed: claude-opus-5 92.9% · low effort 87.9%

    Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made

  • LMArena Text · Chinese 1,550

    #4 of 79 listed models · high effort · CI 1,540–1,560 · 4,449 votes

    Also listed: max effort 1,549

    LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made

  • LMArena Text · Coding 1,533

    #10 of 79 listed models · high effort · CI 1,527–1,540 · 14,606 votes

    Also listed: max effort 1,529

    LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made

  • LMArena Vision 1,321

    #3 of 49 listed models · high effort · CI 1,314–1,329 · 11,599 votes

    LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 13, 2026 · changes we made