Claude Fable 5.1
- Context
- 1M
- 128K max output
- Input price
- $10.00
- per 1M tokens · Claude API
- Output price
- $50.00
- per 1M tokens
- Epoch Capabilities Index
- 165
- #2 of 71 listed
- LMArena Text
- 1,501
- #5 of 79 listed
Where to run it
5 offerings · prices as listed| Meter | Tier | Price |
|---|---|---|
| Input | Standard | $10.00 / 1M tokens |
| Batch | $5.00 / 1M tokens | |
| Output | Standard | $50.00 / 1M tokens |
| Batch | $25.00 / 1M tokens | |
| Cache read | Standard | $0.25 / 1M tokens |
| Cache write | 5-minute cache | $12.50 / 1M tokens |
| 1-hour cache | $20.00 / 1M tokens | |
Amazon Bedrock (opens in a new tab) Claude Fable 5.1 | ||
| Input | Standard | $11.00 / 1M tokens |
| Output | Standard | $55.00 / 1M tokens |
| Cache read | Standard | $0.28 / 1M tokens |
| Cache write | 5-minute cache | $13.75 / 1M tokens |
| 1-hour cache | $22.00 / 1M tokens | |
Google Cloud Vertex AI (opens in a new tab) claude-fable-5-1 | ||
| Input | Standard | $10.00 / 1M tokens |
| Batch | $5.00 / 1M tokens | |
| Prompts over 200K tokens | $10.00 / 1M tokens | |
| Output | Standard | $50.00 / 1M tokens |
| Batch | $25.00 / 1M tokens | |
| Prompts over 200K tokens | $50.00 / 1M tokens | |
| Cache read | Standard | $0.25 / 1M tokens |
| Batch | $0.13 / 1M tokens | |
| Prompts over 200K tokens | $0.25 / 1M tokens | |
| Cache write | 5-minute cache | $12.50 / 1M tokens |
| 1-hour cache | $20.00 / 1M tokens | |
| 5-minute cache · Batch | $6.25 / 1M tokens | |
| 1-hour cache · Batch | $10.00 / 1M tokens | |
| Prompts over 200K tokens · 5-minute cache | $12.50 / 1M tokens | |
| Prompts over 200K tokens · 1-hour cache | $20.00 / 1M tokens | |
Google Cloud Vertex AI (opens in a new tab) Claude Fable 5.1 | ||
| Input | Standard | $11.00 / 1M tokens |
| Batch | $5.50 / 1M tokens | |
| Prompts over 200K tokens | $11.00 / 1M tokens | |
| Output | Standard | $55.00 / 1M tokens |
| Batch | $27.50 / 1M tokens | |
| Prompts over 200K tokens | $55.00 / 1M tokens | |
| Cache read | Standard | $0.28 / 1M tokens |
| Batch | $0.14 / 1M tokens | |
| Prompts over 200K tokens | $0.28 / 1M tokens | |
| Cache write | 5-minute cache | $13.75 / 1M tokens |
| 1-hour cache | $22.00 / 1M tokens | |
| 5-minute cache · Batch | $6.88 / 1M tokens | |
| 1-hour cache · Batch | $11.00 / 1M tokens | |
| Prompts over 200K tokens · 5-minute cache | $13.75 / 1M tokens | |
| Prompts over 200K tokens · 1-hour cache | $22.00 / 1M tokens | |
Google Cloud Vertex AI (opens in a new tab) Claude Fable 5.1 | ||
| Input | Standard | $11.00 / 1M tokens |
| Batch | $5.50 / 1M tokens | |
| Prompts over 200K tokens | $11.00 / 1M tokens | |
| Output | Standard | $55.00 / 1M tokens |
| Batch | $27.50 / 1M tokens | |
| Prompts over 200K tokens | $55.00 / 1M tokens | |
| Cache read | Standard | $0.28 / 1M tokens |
| Batch | $0.14 / 1M tokens | |
| Prompts over 200K tokens | $0.28 / 1M tokens | |
| Cache write | 5-minute cache | $13.75 / 1M tokens |
| 1-hour cache | $22.00 / 1M tokens | |
| 5-minute cache · Batch | $6.88 / 1M tokens | |
| 1-hour cache · Batch | $11.00 / 1M tokens | |
| Prompts over 200K tokens · 5-minute cache | $13.75 / 1M tokens | |
| Prompts over 200K tokens · 1-hour cache | $22.00 / 1M tokens | |
Changes
All changes →- 3 new prices on Claude API Cache write (1-hour cache) $20.00 · Input (Batch) $5.00 · Output (Batch) $25.00
Vendor-reported scores
Published by Anthropic, under the conditions it states| Benchmark | Setting | Score |
|---|---|---|
| SWE-bench Pro | adaptive thinking, max effort, average of 5 trials | 81.2% |
| SWE-bench Multilingual | adaptive thinking, max effort, average of 5 trials | 89.1% |
| SWE-bench Multimodal | adaptive thinking, max effort, average of 5 trials | 54.7% |
| Terminal-Bench 4.0 | adaptive thinking, production safeguards enabled | 55.8% |
| Humanity's Last Exam | no tools, adaptive thinking, max effort | 60.9% |
| with tools, adaptive thinking, max effort | 65% | |
| OSWorld 2.0 | partial score, adaptive thinking, max effort | 77.9% |
| strict score, adaptive thinking, max effort | 41.7% |
Cited scores
From third-party leaderboards, not measured by us- Epoch Capabilities Index 165
#2 of 71 listed models · CI 161.6–169.6
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 1,501
#5 of 79 listed models · max effort · CI 1,495–1,508 · 9,942 votes
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 90.2%
#2 of 56 listed models · max effort · ±1.77
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 1,573
#1 of 79 listed models · max effort · CI 1,550–1,596 · 749 votes
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made
- LMArena Text · Coding 1,529
#16 of 79 listed models · max effort · CI 1,516–1,543 · 2,032 votes
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made
- LMArena Vision 1,322
#2 of 49 listed models · max effort · CI 1,310–1,335 · 2,701 votes
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 13, 2026 · changes we made