Verified November 2026

Home › Compare › Claude Fable 5.1 vs Claude Fable 5.2

Claude Fable 5.1 vs Claude Fable 5.2

A straight cost comparison of Claude Fable 5.1 (Anthropic) and Claude Fable 5.2 (Anthropic), per 1,000,000 tokens, verified November 2026.

$10Claude Fable 5.1 input / 1M
$8Claude Fable 5.2 input / 1M
20%Blended price gap
Claude Fable 5.2Cheaper blended

Rate-by-rate comparison

USD per 1M tokens · November 2026
MetricClaude Fable 5.1Claude Fable 5.2Winner
Input / 1M$10$8Claude Fable 5.2
Cached input / 1M$0.25$0.20Claude Fable 5.2
Cache write / 1M$12.50$10Claude Fable 5.2
Output / 1M$50$40Claude Fable 5.2
Context window1,000,0001,000,000Tie
Batch APIYesYesTie
Long-context tierNoneNone—

For per-token metrics, the lower number wins. For context window and batch support, the higher or broader option wins. A dash means the provider does not publish that rate: a missing cache-write fee means writes are not billed per token, while a missing cached-input rate means cache hits bill at the full input rate.

Blended cost: 1M input + 250K output

ModelBlended costDifference
Claude Fable 5.1$22.50+$4.50
Claude Fable 5.2$18Cheaper

Ten workloads, two bills

The same two models, priced across ten workloads that differ only in their input:output ratio. Nothing else changes — no retries, no system prompt, no middleware.

WorkloadClaude Fable 5.1Claude Fable 5.2Winner
Classification
100K reqs · 500 in / 10 out
$550$440Claude Fable 5.2
Data extraction
10K reqs · 2K in / 200 out
$300$240Claude Fable 5.2
Support chat
1K reqs · 4K in / 600 out
$70$56Claude Fable 5.2
Code review
2K reqs · 8K in / 1.5K out
$310$248Claude Fable 5.2
Summarisation
1K reqs · 20K in / 1K out
$250$200Claude Fable 5.2
Agent loop
5K reqs · 12K in / 2K out
$1,100$880Claude Fable 5.2
Translation
500 reqs · 15K in / 15K out
$450$360Claude Fable 5.2
Long-document QA
200 reqs · 120K in / 800 out
$248$198Claude Fable 5.2
Cached RAG
1K reqs · 50K in (45K cached) / 1K out
$112$89.44Claude Fable 5.2
Nightly batch
10K reqs · 10K in / 2K out
$1,000$800Claude Fable 5.2

Claude Fable 5.1 wins 0 of 10, Claude Fable 5.2 wins 10 of 10. The winner is set by the token mix, not by the headline rate.

Where the two bills cross over

Claude Fable 5.2 is cheaper on both sides of the mix: $8 vs $10 per million input tokens, and $40 vs $50 per million output. No input:output ratio reverses that, so on price alone the other model never becomes the better choice — it has to win on context, latency or output quality.

Cost at four scales

The same support-chat workload (4K input, 600 output per request) at four monthly volumes.

Requests / monthClaude Fable 5.1Claude Fable 5.2Difference
100$7$5.60Claude Fable 5.2 cheaper by $1.40
1,000$70$56Claude Fable 5.2 cheaper by $14
10,000$700$560Claude Fable 5.2 cheaper by $140
100,000$7,000$5,600Claude Fable 5.2 cheaper by $1,400

What caching does to each bill

Caching only helps the part of the prompt that repeats. This is the support-chat workload (1,000 requests, 4,000 input tokens each) with an increasing share of that prompt served from a warm cache, written once on the first request.

Cached share of the promptClaude Fable 5.1Claude Fable 5.2Winner
0%$70$56Claude Fable 5.2
50%$50.52$40.42Claude Fable 5.2
80%$38.84$31.07Claude Fable 5.2
95%$33$26.40Claude Fable 5.2

Both models publish a cached-read rate, so the discount is comparable: Claude Fable 5.1 reads cache at $0.25 per million, Claude Fable 5.2 at $0.20.

Which one should you pick?

Claude Fable 5.1 wins on none of the ten workloads above, while Claude Fable 5.2 wins on classification, data extraction, support chat, code review, summarisation, agent loop, translation, long-document qa, cached rag, nightly batch.

Beyond price, the two differ on input rate ($10 vs $8); output rate ($50 vs $40); cached-input rate ($0.25 vs $0.20); cache-write rate ($12.50 vs $10).

Batch mode is available on Claude Fable 5.1 and Claude Fable 5.2, which halves the nightly job. Both publish cached-input discounts, so a stable system prompt is worth caching on either.

FAQ

Is Claude Fable 5.1 cheaper than Claude Fable 5.2?

On a blended 1M-input-plus-250K-output workload, Claude Fable 5.2 is cheaper by 20% ($18 vs $22.50). The gap changes for cache-heavy prompts and for batch jobs, as the workload table shows.

Which handles longer prompts, Claude Fable 5.1 or Claude Fable 5.2?

Both models share the same 1,000,000-token context window. Neither model publishes a long-context surcharge.

Do both models support prompt caching?

Claude Fable 5.1 bills cached reads at $0.25 per 1M; Claude Fable 5.2 at $0.20.

Related comparisons

Run your own token volumes