Claude Fable 5
No shutdown before this date. Claude Fable 5 stays on Google Vertex AI until at least Jun 8, 2027.
≥ 8 mo- Earliest retirement
- ≥ 237 daysJun 8, 2027 · Google Vertex AI
- Arena Text
- 1,504#4 of 128 · Arena
- GPQA Diamond
- 85.9%#54 of 108 · Epoch AI
- List price · $ per 1M
- $10.00 in $50.00 outClaude API · cached input $1.00
- Context window
- 1MMax output 128K tokens
Dates on every platform
| Platform | Model ID and status | Deprecated | Shuts down | Replacement |
|---|---|---|---|---|
| Claude APIAnthropic: Model deprecations (opens in a new tab) · checked Oct 14, 2026 | claude-fable-5Legacy | – | ≥ 8 moNot sooner than | – |
| Azure AI FoundryMicrosoft: Model retirement schedule - Microsoft Foundry (opens in a new tab) · checked Oct 14, 2026 | claude-fable-5:1Preview | – | ≥ 14 moNot sooner than | – |
| Amazon BedrockAmazon Web Services: Amazon Bedrock ListFoundationModels, us-east-1 (opens in a new tab) · checked Oct 14, 2026 | anthropic.claude-fable-5Active · also global.anthropic.claude-fable-5, us.anthropic.claude-fable-5 | – | ≥ 8 moNot sooner than | – |
| Google Vertex AIGoogle Cloud: Claude Fable 5 on Google Cloud (opens in a new tab) · checked Oct 14, 2026 | claude-fable-5Active | – | ≥ 8 moNot sooner than | – |
Anthropic lists it as a legacy model and recommends Claude Fable 5.1.
Version 1 runs on Anthropic infrastructure.
Preview dates on Azure are a floor. Preview deployments are upgraded to a newer version or retired with at least 30 days' notice.
In us-east-1, requests go through a cross-Region inference profile (listed in aliases).
What breaks when you move off Claude Fable 5
No breaking changes are recorded for the move to Claude Fable 5.1. Run your own cases on it before the date.
Intelligence
| Benchmark | Publisher | Score | Rank | Published |
|---|---|---|---|---|
| Arena Text | Arena | 1,504 ± 2 | #4 of 128 | Oct 8, 2026 |
| GPQA Diamond | Epoch AI | 85.9% ± 2.5% | #54 of 108 | Aug 6, 2026 |
| Arena WebDev | Arena | 1,625 ± 3 | #11 of 69 | Oct 8, 2026 |
| Arena Agent | Arena | 0 ± 0 | #8 of 35 | Oct 12, 2026 |
| FrontierMath Tier 4 | Epoch AI | 90.2% ± 4.6% | #4 of 58 | Jun 9, 2026 |
| FrontierMath Tiers 1-3 | Epoch AI | 87.0% ± 2.0% | #9 of 71 | Jun 9, 2026 |
| OTIS Mock AIME 2024-2025 | Epoch AI | 100.0% ± 0.0% | #1 of 105 | Aug 6, 2026 |
| SimpleQA Verified | Epoch AI | 70.7% ± 1.4% | #7 of 68 | Aug 10, 2026 |
Arena (arena.ai), https://arena.ai/leaderboard
Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource].
List prices
| Platform | Input | Cached | Output | In effect | Source |
|---|---|---|---|---|---|
Claude APIclaude-fable-5 | $10.00 | $1.00 | $50.00 | Jun 9, 2026Current | Anthropic: Pricing (opens in a new tab) |
Amazon Bedrockanthropic.claude-fable-5 | $11.00 | $1.10 | $55.00 | Sep 1, 2026Current · Standard tier, in-Region or geographic cross-Region inference, which Bedrock prices 10% above global cross-Region inference. | Amazon Web Services: AWS Price List API: AmazonBedrockFoundationModels, us-east-1 (opens in a new tab) |
Google Vertex AIclaude-fable-5 | $10.00 | $1.00 | $50.00 | Jun 9, 2026Current · Global endpoint price; regional and multi-region endpoints cost more. | Google Cloud: Agent Platform pricing (opens in a new tab) |