Claude Opus 4.8
- Context
- 1M
- 128K max output
- Input price
- $5.00
- per 1M tokens · Claude API
- Output price
- $25.00
- per 1M tokens
- Epoch Capabilities Index
- 158.3
- #10 of 71 listed
- LMArena Text
- 1,480
- #17 of 79 listed
Where to run it
7 offerings · prices as listed| Meter | Tier | Price |
|---|---|---|
| Input | Standard | $5.00 / 1M tokens |
| Batch | $2.50 / 1M tokens | |
| Output | Standard | $25.00 / 1M tokens |
| Batch | $12.50 / 1M tokens | |
| Cache read | Standard | $0.50 / 1M tokens |
| Cache write | 5-minute cache | $6.25 / 1M tokens |
| 1-hour cache | $10.00 / 1M tokens | |
Amazon Bedrock (opens in a new tab) Claude Opus 4.8 | ||
| Input | Standard | $5.50 / 1M tokens |
| Output | Standard | $27.50 / 1M tokens |
| Cache read | Standard | $0.55 / 1M tokens |
| Cache write | 5-minute cache | $6.88 / 1M tokens |
| 1-hour cache | $11.00 / 1M tokens | |
Amazon Bedrock (opens in a new tab) Claude Opus 4.8 | ||
| Input | Standard | $5.50 / 1M tokens |
| Output | Standard | $27.50 / 1M tokens |
| Cache read | Standard | $0.55 / 1M tokens |
| Cache write | 5-minute cache | $6.88 / 1M tokens |
| 1-hour cache | $11.00 / 1M tokens | |
Amazon Bedrock (opens in a new tab) Claude Opus 4.8 | ||
| Input | Standard | $5.50 / 1M tokens |
| Output | Standard | $27.50 / 1M tokens |
| Cache read | Standard | $0.55 / 1M tokens |
| Cache write | 5-minute cache | $6.88 / 1M tokens |
| 1-hour cache | $11.00 / 1M tokens | |
Google Cloud Vertex AI (opens in a new tab) claude-opus-4-8 | ||
| Input | Standard | $5.00 / 1M tokens |
| Batch | $2.50 / 1M tokens | |
| Prompts over 200K tokens | $5.00 / 1M tokens | |
| Output | Standard | $25.00 / 1M tokens |
| Batch | $12.50 / 1M tokens | |
| Prompts over 200K tokens | $25.00 / 1M tokens | |
| Cache read | Standard | $0.50 / 1M tokens |
| Batch | $0.25 / 1M tokens | |
| Prompts over 200K tokens | $0.50 / 1M tokens | |
| Cache write | 5-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 (opens in a new tab) Claude Opus 4.8 | ||
| Input | Standard | $5.50 / 1M tokens |
| Batch | $2.75 / 1M tokens | |
| Prompts over 200K tokens | $5.50 / 1M tokens | |
| Output | Standard | $27.50 / 1M tokens |
| Batch | $13.75 / 1M tokens | |
| Prompts over 200K tokens | $27.50 / 1M tokens | |
| Cache read | Standard | $0.55 / 1M tokens |
| Batch | $0.28 / 1M tokens | |
| Prompts over 200K tokens | $0.55 / 1M tokens | |
| Cache write | 5-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 (opens in a new tab) Claude Opus 4.8 | ||
| Input | Standard | $5.50 / 1M tokens |
| Batch | $2.75 / 1M tokens | |
| Prompts over 200K tokens | $5.50 / 1M tokens | |
| Output | Standard | $27.50 / 1M tokens |
| Batch | $13.75 / 1M tokens | |
| Prompts over 200K tokens | $27.50 / 1M tokens | |
| Cache read | Standard | $0.55 / 1M tokens |
| Batch | $0.28 / 1M tokens | |
| Prompts over 200K tokens | $0.55 / 1M tokens | |
| Cache write | 5-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 →- 3 new prices on Claude API Cache write (1-hour cache) $10.00 · Input (Batch) $2.50 · Output (Batch) $12.50
Cited scores
From third-party leaderboards, not measured by us- Epoch Capabilities Index 158.3
#10 of 71 listed models · CI 156.3–161
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 1,480
#17 of 79 listed models · high effort · CI 1,476–1,484 · 61,560 votes
Also listed: claude-opus-4-8 1,474
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 80%
#11 of 56 listed models · max effort · ±2.37
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 91%
#20 of 64 listed models · max effort · ±1.92
Also listed: low effort 88.4% · reasoning off 85.4%
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 1,527
#19 of 79 listed models · CI 1,517–1,537 · 4,274 votes
Also listed: high effort 1,525
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made
- LMArena Text · Coding 1,534
#9 of 79 listed models · high effort · CI 1,528–1,540 · 16,899 votes
Also listed: claude-opus-4-8 1,530
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made
- LMArena Vision 1,292
#16 of 49 listed models · high effort · CI 1,285–1,299 · 15,274 votes
Also listed: claude-opus-4-8 1,288
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 13, 2026 · changes we made