Comparison · upgrade decision

Claude Fable 5.1 vs Claude Fable 5

Claude Fable 5.1 outscores Claude Fable 5 on all nine benchmarks Anthropic published for both, most widely on Terminal-Bench-Science 0.1 at 52.6% against 24.7%. List prices are identical. The only price difference is the cache read rate, $0.25 against $1.00 per 1M tokens.

Benchmark scoreboard

Nine evaluations, side by side. Fable 5.1 leads on every row.

BenchmarkFable 5.1Fable 5Delta
Terminal-Bench-Science 0.152.6%24.7%+27.9
Terminal-Bench 4.055.8%42.0%+13.8
CursorBench 3.2.073.4%70.5%+2.9
OSWorld 2.0 (partial)77.9%72.9%+5.0
OSWorld 2.0 (strict)41.7%36.1%+5.6
HLE (no tools)60.9%57.8%+3.1
HLE (with tools)65.0%63.8%+1.2
AutomationBench31.4%17.1%+14.3
GDPval-AA v218531723+130

The cache arithmetic on three profiles

Cost equals uncached input times the input rate plus cached input times the cache-read rate plus output times the output rate. Cache WRITE cost is excluded because a long-running agent writes the prefix once and reads it many times.

ProfileInput tokensHit rateOutput tokensFable 5.1Fable 5Saving
A. Chat / short prompt200K20%20K$2.61$2.641.1%
B. Typical agentic session10M90%200K$22.25$29.0023.3%
C. Long-running cache-heavy agent20M95%100K$19.75$34.0041.9%

Should you upgrade?

On profile A the saving is about 1% and not worth a migration. On profiles B and C the upgrade pays back on the first session. Anthropic's claim of "about 25% cheaper for typical workloads, up to about 45% for agentic work" reproduces from the published rates alone.

Ready to test the workflow?

Create account & add credits

Migration

Migrating from claude-fable-5 to claude-fable-5.1 is a one-line model-string change. Two behaviour caveats: thinking blocks are model-specific and cannot be replayed into a different model; accounts created on or after 31 August 2026 cannot edit prior context mid-conversation.

Is Claude Fable 5 going away?

No. Anthropic has not published an end-of-life date for Claude Fable 5. The 1 September 2026 release of Claude Fable 5.1 is additive rather than a replacement, and both model identifiers, claude-fable-5 and claude-fable-5.1, resolve today. Pricing on Claude Fable 5 is unchanged at $10 per 1M input and $50 per 1M output tokens, with cache reads at $1.00 per 1M.

Frequently asked questions

Which is cheaper, Claude Fable 5.1 or Claude Fable 5?

It depends entirely on how much cached context you re-read per token generated, because list prices are identical at $10 per 1M input and $50 per 1M output. The only difference is the cache read rate, $0.25 against $1.00. On a short prompt at a 20% hit rate the saving is about 1%; on a long-running agent at a 95% hit rate the saving is about 42%.

Should you upgrade from Claude Fable 5 to 5.1?

Whether you should upgrade from Claude Fable 5 to 5.1 turns on how much cached context you re-read per token generated. On a chat-shaped workload the saving is about 1%; on a long-running agent it reaches about 42%. Anthropic's claim of "about 25% typical, up to 45% agentic" reproduces from the published rates alone.

Put Claude Fable 5.1 to work

Fund a controlled evaluation, start with a prepared prompt, and measure quality and cost on your own workload.