New Sign up free, 10 calls on us. Up to $1, no card needed.

Claude Fable 5 vs Claude Fable 5.1

Claude Fable 5 has been retired from our catalogue. Its figures below are the last published rates; calls to it are no longer served, while the other model in this comparison is.

Claude Fable 5.1 is served by invitation. Its figures below are the live rates, but calls need a workspace grant first; ask us for access before you build on this comparison.

vs

Which one, when

These two are near-identical on the facts: both take text and image in, both return text, both carry a 1000000-token context with 128000 max output, the same chat, code, thinking, tools and reasoning flags, thinking that cannot be disabled, and the same $10 input and $50 output per million tokens. The separation is cache reads and recency: claude-fable-5-1 charges $0.25 per million cached input tokens against $1 for claude-fable-5, a 4x difference, and carries a 2026-06 knowledge cutoff versus 2026-01. Pick 5.1 for cache-heavy or repeated-prefix workloads; stay on claude-fable-5 only if you are already pinned to it.

Benchmarks

LeadsAbove averageNo peer higherClaude Fable 5083 / 9143 / 91Claude Fable 5.177 / 77 / 7

7 measured on both.

Claude Fable 5 Claude Fable 5.1 other models measured peer average no peer scored higher
Terminal-bench 4.0
42%
no peer scored higher 55.8%
BioMysteryBench hard
46.5%
N/A
OSWorld 2.0 partial
72.9%
77.9%
Cybergym
83.1%
N/A
HealthBench Professional
no peer scored higher 60.9%
N/A
GDPval-AA v2 Elo · 1711-1853 per Anthropic · 2026-09-05
1723
no peer scored higher 1853
Harvey Lab-AA
93.6%
N/A
Humanity's Last Exam no tools
57.8%
no peer scored higher 60.9%
Blueprint-Bench 2
38.6%
N/A
AutomationBench
17.1%
no peer scored higher 31.4%
CharXiv (RQ) reasoning
no peer scored higher 88.9%
N/A

Vendor-published: Alibaba (Qwen) Anthropic ByteDance DeepSeek Google MiniMax Moonshot OpenAI Tencent Z.ai

Pricing

Claude Fable 5 Claude Fable 5.1 Δ
Input / 1M tokens $10 $10 =
Output / 1M tokens $50 $50 =
Cache read / 1M tokens $1 $0.25
Cache write 1.25x (5m) / 2x (1h) 1.25x (5m) / 2x (1h) -

Rates from the live catalog at build time; each model page carries the current card.

Where they sit - input price per 1M tokens across all 67 chat models on this billing unit (log scale)

Capabilities

Claude Fable 5 Claude Fable 5.1
Tool use yes yes
Thinking control always on always on
Structured output yes yes
Prompt caching explicit (you mark the prefix) explicit (you mark the prefix)
Cache lifetime 5m default, 1h option 5m default, 1h option
Minimum cached prefix 1024 tokens 1024 tokens

Specs

Claude Fable 5 Claude Fable 5.1
Input modalities text image text image
Output modalities text text
Released 2026-06-09 2026-09-01
Knowledge cutoff 2026-01 2026-06
Context window 1M 1M
Max output 128K 128K
Thinking parameter output_config.effort (thinking.type is adaptive-only and needs no configuration) output_config.effort (thinking is adaptive-only and always on)
Accepted values
effort
  • low
  • medium
  • high
  • xhigh
  • max

both "enabled" and "disabled" return 400

effort
  • low
  • medium
  • high
  • xhigh
  • max
Default

thinking always on (adaptive)

effort
  • high

thinking always on (adaptive)

effort
  • high

Specs are transcribed from each vendor’s documentation; a row a vendor does not publish is left out rather than inferred. Full sources: Claude Fable 5 · Claude Fable 5.1

Switch between them with one line

Both ids are in every tab below - the highlighted pair of lines is the only edit. Same endpoint, same key, same request shape.

from openai import OpenAI

client = OpenAI(
    base_url="https://synthorai.io/v1",
    api_key="sk-syn-...",
)

resp = client.chat.completions.create(
    model="claude-fable-5",
    # model="claude-fable-5-1",  # uncomment this line, comment the one above
    messages=[{"role": "user", "content": "Summarize this diff"}],
    reasoning_effort="medium",
)
print(resp.choices[0].message.content)

Get your API key →

FAQ

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

They list the same input / 1m tokens ($10), so price does not decide this one - see the specs and capabilities below.

Can I A/B test Claude Fable 5 against Claude Fable 5.1 without two integrations?

Yes. Both are served through the same OpenAI-compatible endpoint with one API key - switching is a one-line model-string change, so you can route a fraction of traffic to each and compare bills directly.

Do Claude Fable 5 and Claude Fable 5.1 support prompt caching?

Yes - both bill cached reads below their input rate, so warm-prefix workloads cost less than the list rates suggest. The exact cache-read rows are in the pricing table above.

Related comparisons

From our measured studies