llmrelay
// claude

Claude Fable 5.1

Current Fable. Same $10/$50 list as Fable 5, cheaper cache reads.

Claude Fable 5.1 is the current Fable — Anthropic’s narrative and creative specialist, the model for long-form writing, character consistency, and voice. Input and output list prices are unchanged from Fable 5: $10 / $50 per million tokens.

The real change is cache. Official cache hits on 5.1 are $0.25/M, a quarter of Fable 5’s $1/M. Anthropic prices that at 0.025× input instead of the usual 0.1×. We do not currently pass a CacheRatio through to the bill, so that cheaper cache is margin for us rather than a discount on the invoice.

We sell it at half Anthropic’s list — $5.00 per million input tokens against $10.00, same as Fable 5. The model id on the API is claude-fable-5-1 (hyphen, not a dot).

Official list
llmrelay
Input / M tokens
$10.00
$5.00
Output / M tokens
$50.00
$25.00
Context window
—
1,000,000 tokens
Max output
—
128,000 tokens

What it costs you per month

Real-world budget scenarios. Numbers are simple sums — official list price vs llmrelay's 50% off tier.

Usage scenario
Official
llmrelay
Light coding (1M in / 200K out per month)
$20.00
$10.00save $10.00
Heavy Cursor / Cline user (50M in / 5M out per month)
$750.00
$375.00save $375.00
Production RAG (500M in / 20M out per month)
$6000.00
$3000.00save $3000.00

What it's good at

Best for

Pick Claude Fable 5.1 when

  • +Long-form narrative writing: fiction, scripts, newsletters, campaign content. Fable is tuned for voice and flow in a way the reasoning models are not.
  • +Character consistency across a long work. If you are drafting a novel or a campaign with recurring voices, Fable holds characterisation better than Opus.
  • +Marketing and brand copy where tone is load-bearing. Product descriptions, landing pages, email sequences — work where sounding human is part of the job.
  • +You were on Fable 5 and want the current point release. Same per-token rate, newer snapshot, cheaper cache on Anthropic’s own card.

Choose something else when

  • !Coding, reasoning, or agent work. Fable is not a reasoning model. If you need it to debug code or plan a multi-step workflow, use Opus or Sonnet.
  • !Structured output or API responses. Fable’s tuning optimises for natural language, not JSON schema compliance or function calling.
  • !Work where factual accuracy is the only thing that matters. Technical documentation, legal copy, financial summaries — those are Opus jobs.
  • !High-volume batch work on a budget. At $5/M input Fable is expensive. If the task is classification or extraction rather than narrative, use Sonnet or Haiku.

Questions people ask about Claude Fable 5.1

How much does Claude Fable 5.1 cost?

Anthropic’s list price is $10.00 per million input tokens and $50.00 per million output tokens — the same as Fable 5. On llmrelay it is $5.00 and $25.00, exactly half list. Official cache hits on 5.1 are $0.25/M versus $1/M on Fable 5; we do not currently pass that cache discount through to the bill.

What is the model id?

claude-fable-5-1. Use the hyphen, not claude-fable-5.1 — that spelling returns no available channel.

Should I use Fable 5.1 or Opus 5 for writing?

Fable 5.1 if the output is narrative, marketing, or creative — anything where voice and flow matter. Opus 5 if it is technical, structured, or factual. Fable costs twice Opus per token on llmrelay, so do not pick it as a general upgrade.

What is the context window on Claude Fable 5.1?

1,000,000 tokens input, with up to 128,000 output tokens. That is the same window as Fable 5, Opus 5 and Sonnet 5.

Try Claude Fable 5.1 at half the price

Free to create an account, no subscription, $10 minimum top-up — enough to run this model against a real task and judge quality yourself.

Get API key →

Compare Claude Fable 5.1 against the alternatives

The comparisons this model appears in, the models nearest it on price, and the full rate card.