# Claude Fable 5.1

> Claude Fable 5.1 is the current top of Anthropic's generally available lineup, succeeding Fable 5. It is built for autonomous coding, long-horizon agents, and the kind of analysis where a half-right answer is worth nothing. 1M-token context window, native prompt caching, vision input.

Canonical: https://routemux.com/anthropic/claude-fable-5-1
Provider: Anthropic

## Key facts

| Field | Value |
| --- | --- |
| Model ID | anthropic/claude-fable-5-1 |
| Official model ID | claude-fable-5-1 |
| Context window | 1M |
| Max output | 8K |
| Input modalities | text, image |
| Output modalities | text |
| Capabilities | Vision, Reasoning, Tool Calling, Coding, Cache |
| Upstream release | 2026-09-01 |
| Availability | available |

## Pricing

- RouteMux input: $2.8 per 1M tokens
- RouteMux output: $14 per 1M tokens
- Official input: $10 per 1M tokens
- Official output: $50 per 1M tokens
- Cache read: $0.07 per 1M tokens
- Cache write: $3.5 per 1M tokens
- Saving vs official: 72%
- Official price source: anthropic_x0.28, verified 2026-09-02

Billing is prepaid wallet, charged per successful request only.

## API access

Base URL: https://api.routemux.com

Supported protocols:

- anthropic_messages

## What is Claude Fable 5.1

Claude Fable 5.1 is the current top of Anthropic's generally available lineup, succeeding Fable 5. It is built for autonomous coding, long-horizon agents, and the kind of analysis where a half-right answer is worth nothing. 1M-token context window, native prompt caching, vision input.

Through RouteMux it is $2.80 per 1M input tokens against Anthropic's $10, and $14 against $50 on output — the same per-token price as Fable 5. Same model, same Anthropic Messages API, billed from a prepaid wallet instead of an Anthropic account, with failed and timed-out requests not charged.

What actually changed is caching. Anthropic prices cache reads on Fable 5.1 at 2.5% of the base input rate rather than the usual 10%, which lands at $0.07 per 1M tokens here — a quarter of what Fable 5 costs. Long sessions, large system prompts, and agents that re-read the same codebase are where that shows up.

It still sits above Opus 5 and still costs twice as much per token, so the honest way to choose has not changed: try Opus 5 first, and move up only when it is demonstrably not enough.

## Key capabilities

- **Top of the generally available lineup** — Anthropic positions it as its most capable GA model for autonomous coding and long-horizon work, succeeding Fable 5.
- **Cache reads at a quarter the price** — Anthropic bills cache reads at 2.5% of base input on this model instead of the usual 10% — $0.07 per 1M tokens here. The more you hit cache, the wider the gap with Fable 5.
- **Thinking is always on** — No thinking budget to set — and none accepted. Depth is controlled by the effort level instead.
- **Anthropic Messages native** — No translation layer; the request is the same one you would send to Anthropic directly.

## Other variants in this family

- Claude Fable 5 (`anthropic/claude-fable-5`)

## Sources

- [Anthropic — Models overview](https://docs.anthropic.com/en/docs/about-claude/models)
- [Anthropic — Pricing (cache multiplier footnote)](https://platform.claude.com/docs/en/about-claude/pricing)

_Content reviewed by Jerry Fan on 2026-09-02._