Anthropic
Claude Fable 5.1: price, context window, and caching
Anthropic's most capable generally available model, aimed at demanding reasoning and long-horizon agentic coding. Anthropic suggests it when Opus-tier results fall short.
Released September 1, 2026 · Prices as of September 26, 2026
In Anthropic’s words
“They're the world's most advanced models for coding and knowledge work”
What Anthropic says it’s good at
Facts
Specs and prices
| Fact | Claude Fable 5.1 |
|---|---|
| Maker | Anthropic |
| API model id | claude-fable-5-1 |
| Released | September 1, 2026 |
| Status | Current |
| Context window | 1M tokens |
| Max output | 128K tokens |
| Open weights | No |
| Input, per 1M tokens | $10 |
| Cache hit, per 1M | $0.25 |
| Cache write, per 1M | $12.50 (5-minute), $20 (1-hour) |
| Output, per 1M tokens | $50 |
| Runs in | Claude Code, Cursor, OpenCode, OpenRouter, and GitHub Copilot |
Standard API rates in US dollars, as published by the maker on September 26, 2026. Batch and priority tiers, taxes, and subscription plans are not included. Claude Fable 5.1: The full 1M context window is billed at standard rates.
Good to know
- Like every Claude model from 4.7 on, it uses Anthropic's newer tokenizer, which counts about 30% more tokens than earlier Claude models for the same text.
- Adaptive thinking is always on. Effort runs from low to max, and the default is high.
- In Claude Code you choose it with /model fable. It is not the default on any plan.
- It requires 30-day data retention, so it is not available under zero data retention.
Cost
What typical work costs
Example token counts at Claude Fable 5.1’s published rates. On the agentic session, caching saves $17.00 against billing every token as ordinary input.
| Agentic coding session, 100K input, 400K written to cache, 2M read from cache, 50K output | $10.50 |
|---|---|
| Large one-off review, 150K input with no cache hits, 10K output | $2.00 |
| Output-heavy generation, 30K input, 80K output | $4.30 |
| A month of sessions, 110 sessions: 5 a day, 22 working days | $1,155.00 |
Prompt caching
How Anthropic bills cached tokens
Anthropic
Claude caches a prompt prefix up to a breakpoint. One top-level cache_control field places the breakpoint automatically and moves it as the conversation grows, or you can mark up to 4 blocks yourself. Claude Code manages caching for you.
A 5-minute cache write costs 1.25x the input price and a 1-hour write costs 2x. A cache hit costs 0.1x input on most models, 0.05x on Claude Opus 5.5, and 0.025x on Claude Fable 5.1 and Claude Mythos 5.1. Every hit restarts the cache lifetime at no charge.
Anthropic's rule of thumb: a 5-minute write pays for itself after one cache read, and a 1-hour write after two.
In Claude Code, the main conversation uses the 1-hour cache on a Claude subscription and the 5-minute cache with an API key. Each model has its own cache, so switching models starts over.
Source: Anthropic: Prompt caching
Claude Fable 5.1 compared
Claude Fable 5.1 vs Claude Fable 5
Claude Fable 5.1 keeps Claude Fable 5's rates but cuts a cache hit from $1 to $0.25 per million. What that saves on agentic sessions, and what it doesn't.
Claude Fable 5.1 vs Claude Mythos 5.1
Claude Mythos 5.1 is Claude Fable 5.1 with more permissive safeguards and invitation-only access. Prices match, down to $0.25 per million for a cache hit.
Claude Fable 5.1 vs Claude Opus 5.5
Claude Fable 5.1 lists at 2.5x the rates of Claude Opus 5.5. What that premium buys, why cheap cache hits barely narrow it, and when Anthropic suggests it.
Claude Fable 5.1 vs Claude Sonnet 5
Claude Fable 5.1 lists at 5x the rates of Claude Sonnet 5, but cache hits cost $0.25 against $0.20. Why sessions cost 4.4x, and who Anthropic aims Fable 5.1 at.
Claude Fable 5.1 vs Gemini 3.1 Pro Preview
A cached coding session costs 5.3x more on Claude Fable 5.1 than on Gemini 3.1 Pro Preview, mostly from cache writes. Output limits and preview status compared.
Claude Fable 5.1 vs Gemini 3.8 Flash
A cached coding session costs 14.8x more on Claude Fable 5.1 than on Gemini 3.8 Flash. How Flash's introductory rates, output cap, and free tier factor in.
Claude Fable 5.1 vs GPT-5.6 Sol
GPT-5.6 Sol costs 60% less than Claude Fable 5.1 at promotional rates available at least through November 21, 2026. Why caching leaves the 2.5x gap intact.
Claude Fable 5.1 vs GPT-6 Astra
Claude Fable 5.1 and GPT-6 Astra share $10 input and $50 output prices, and a cached coding session costs $10.50 on each. Caching decides which way it tips.
Claude Fable 5.1 vs GPT-6 Sol
Claude Fable 5.1 costs 5x what GPT-6 Sol does per token, and caching leaves that ratio intact. How Anthropic's top model compares with OpenAI's middle one.
Your own numbers
See what Claude Fable 5.1 really costs you.
everyaitoken reads your Claude Code, Cursor, OpenCode, and OpenRouter history on your Mac and prices every request at API rates, with what caching saved or cost. $9 once.