Verified October 2026

Home › Models › Claude Fable 5.1

Claude Fable 5.1 API pricing

Claude Fable 5.1 is a flagship model from Anthropic with a 1,000,000-token context window. Rates below are per 1,000,000 tokens, verified October 2026.

$10Input / 1M tokens
$50Output / 1M tokens
$0.25Cached input / 1M
1,000,000Context window

Price list

Claude Fable 5.1 rates in USD per 1M tokens, October 2026
Token classRate / 1MNotes
Input$10Prompt tokens not served from cache
Cached input$0.2598% below base input
Cache write$12.50Charged once when the prefix is stored
Output$505.0× the input rate
Batch API−50%Input and output, results within 24 h

Released Sep 1, 2026. Cache read cut 75% ($1.00 → $0.25).

What Claude Fable 5.1 costs at three real workloads

Sticker prices rarely match the invoice. These three workloads use the rates above, with cache writes charged once per job and the batch discount applied only where the provider offers it.

WorkloadRequestsTokensEstimated cost
Support chat1,0004K in / 600 out$70
RAG with caching1,00050K in (45K cached) / 1K out$112
Nightly batch job10,00010K in / 2K out$1000

Caching the 45K-token prefix saves about 80% on the RAG workload versus sending it uncached every call ($550 → $112). Batch mode halves the nightly job.

Where Claude Fable 5.1 sits in the market

Out of 28 models in this dataset, Claude Fable 5.1 ranks #28 cheapest by input rate, #28 by output rate, and #28 on a blended 1M-input-plus-250K-output workload.

ModelProviderInputOutputBlended
Claude Fable 5.1Anthropic$10$50$22.50
GPT-6 AstraOpenAI$10$50$22.50
GPT-5.5OpenAI$5$30$12.50
Claude Opus 5Anthropic$5$25$11.25

Blended cost = 1M input tokens + 250K output tokens at list price.

FAQ

How much does Claude Fable 5.1 cost per 1M tokens?

$10 per 1M input tokens and $50 per 1M output tokens on the standard tier.

Is prompt caching cheaper on Claude Fable 5.1?

Yes. Cached input bills at $0.25 per 1M tokens, 97.5% below the $10 base input rate, with a one-off cache write at $12.50 per 1M.

Does Claude Fable 5.1 support the Batch API?

Yes. Batch requests bill at roughly half the standard input and output rates: the nightly job above costs $2000 at list price and about $1000 in batch mode.

Keep reading

Run these numbers in the calculator