# Claude Fable 5 vs Claude Fable 5.1

As of October 21, 2026, Claude Fable 5 and Claude Fable 5.1 cost the same: $10.00 per 1M input tokens and $50.00 per 1M output tokens, and both have a 1M-token context window.

- Page: https://models.litellm.ai/compare/claude-fable-5-vs-claude-fable-5-1
- Claude Fable 5: https://models.litellm.ai/models/claude-fable-5
- Claude Fable 5.1: https://models.litellm.ai/models/claude-fable-5-1

## Side by side

| | Claude Fable 5 | Claude Fable 5.1 |
|---|---|---|
| Input, per 1M tokens | $10.00 | $10.00 |
| Output, per 1M tokens | $50.00 | $50.00 |
| Cache read, per 1M tokens | $1.00 | $0.25 |
| Cache write, per 1M tokens | $12.50 | $12.50 |
| Context window | 1,000,000 tokens | 1,000,000 tokens |
| Max output | 128,000 tokens | 128,000 tokens |
| Image input | Yes | Yes |
| Tool calling | Yes | Yes |
| Structured output (JSON) | Yes | Yes |
| Prompt caching | Yes | Yes |
| Reasoning | Yes | Yes |
| Providers on LiteLLM | 9 | 7 |
| Price shown is from | Anthropic | Anthropic |
| Added to LiteLLM | June 2026 | September 1, 2026 |

Headline prices in USD per 1M tokens, from LiteLLM's model price file.

## Cheapest provider for each

- Claude Fable 5: Anthropic at $10.00 input per 1M tokens (`claude-fable-5`)
- Claude Fable 5.1: Anthropic at $10.00 input per 1M tokens (`claude-fable-5-1`)

## Benchmark scores

| Benchmark | Claude Fable 5 | Claude Fable 5.1 |
|---|---|---|
| Epoch Capabilities Index (Overall) | 163.4 | 166.5 |
| FrontierCode (Coding and agents) | 53.5% | 50.9% (medium) |
| FrontierSWE (Coding and agents) | 47.0% (max) | 56.3% (max) |
| APEX-Agents (Coding and agents) | 63.6% | 68.6% |
| ARC-AGI-2 (Reasoning and knowledge) | 89.2% (max) | 90.0% (max) |
| SimpleQA Verified (Reasoning and knowledge) | 70.7% (xhigh) | 70.8% (max) |
| FrontierMath (tiers 1-3) (Math) | 87.0% (max) | 90.2% (max) |
| FrontierMath (tier 4) (Math) | 90.2% (max) | 87.8% (max) |
| OTIS Mock AIME 2024-2025 (Math) | 100.0% (high) | 100.0% (max) |

From the Epoch AI Benchmarking Hub (https://epoch.ai/benchmarks), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/), data as of September 1, 2026: Epoch's own runs and results it collects from each benchmark's leaderboard. Higher is better.

## FAQ

### Which is cheaper, Claude Fable 5 or Claude Fable 5.1?

They cost the same: $10.00 per 1M input tokens and $50.00 per 1M output tokens, as of October 21, 2026.

### Which has the larger context window, Claude Fable 5 or Claude Fable 5.1?

Both have a 1,000,000-token context window.

### Can I switch from Claude Fable 5 to Claude Fable 5.1 without changing my code?

Yes. Through LiteLLM both use the OpenAI format, so switching means changing the model name from "claude-fable-5" to "claude-fable-5-1", or pointing a LiteLLM gateway model alias at the other model. You can also use one as a fallback for the other.