modelbenchmark.io

Claude Fable 5.1

Anthropic · claude-fable-5-1

Compare

Claude model for demanding reasoning and long-horizon agentic work

Specification

anthropic listing

Context
1M
Max output
128K
Released
2026-09-01
Knowledge cutoff
2026-06
Retires
2027-09-01
Open weights
no
Input
text, image, pdf
Output
text

Price

US dollars per million tokens · anthropic list price

Input
$10.00
Output
$50.00
Cache read
$0.25
Cache write
$12.50

Batch and priority prices

US dollars per million tokens · per listing

PriceListing$/M
Cache write, 1 hourbedrock_converse$20.00
Cache write, 1 hourbedrock_converse · us$22.00
Cache write, 1 hourbedrock$24.00

Quality

10 benchmarks · 2 sources

Composite
99th
percentile of 334 scored models
Rank
5 / 334
±0.08 sd
Evidence
10 × 2
3 or more benchmarks, from 2 or more sources
Effort range
one configuration only
coding100th1/3 bench
reasoning99th3/4 bench
math97th3/7 bench
knowledge97th1/1 bench
general100th1/1 bench

By reasoning effort

every setting placed on the same scale as the leaderboard

SettingCompositeBenchmarks behind it
max99th8
high98th1

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
Mystery Game Puzzles58.0 ±5.0maxEpoch AI2026-09-01
Chess Puzzles47.0 ±5.0maxEpoch AI2026-09-01
FrontierMath-Tier-4-v287.8 ±5.2maxEpoch AI2026-09-01
FrontierMath-Tiers-1-3-v290.2 ±1.8maxEpoch AI2026-09-01
EBR-bench57.1 ±6.0maxEpoch AI2026-09-08
LiveBench83.8max · 23 runsLiveBench2026-06-25
MirrorCode73.3highEpoch AI2026-09-10
SimpleQA Verified70.8 ±1.4maxEpoch AI2026-09-01
OTIS Mock AIME 2024-2025100.0 ±0.0maxEpoch AI2026-09-01
FrontierMath-Erdos0.0 ±0.0maxEpoch AI2026-09-01

The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.

Available from 33 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
anthropicvendor$10.00$50.00$0.25$12.501M128K2027-09-01
302ai$10.00$50.001M128K
amazon-bedrock$10.00$50.00$0.25$12.501M128K
amazon-bedrock · global$10.00$50.00$0.25$12.501M128K
azure$10.00$50.00$0.25$12.501M128K
azure_ai$10.00$50.00$0.25$12.501M128K2027-12-05
azure-cognitive-services$10.00$50.00$0.25$12.501M128K
bedrock_converse$10.00$50.00$0.25$12.501M128K
bedrock_converse · global$10.00$50.00$0.25$12.501M128K
cloudflare-ai-gateway$10.00$50.00$0.25$12.501M128K
crossmodel$10.00$50.00$0.25$12.501M128K
edenai$10.00$50.00$0.25$12.501M128K
github-copilot$10.00$50.00$0.25$12.501M128K
kilo$10.00$50.00$0.25$12.501M128K
llmgateway$10.00$50.00$0.25$12.501M128K
llmgateway-providers$10.00$50.00$0.25$12.501M128K
llmgateway-providers · aws-bedrock$10.00$50.00$0.25$12.501M128K
merge-gateway$10.00$50.00$0.25$12.501M128K
nano-gpt$10.00$50.00$0.25$12.501M128K
neon$10.00$50.00$0.25$12.501M128K
ofox$10.00$50.00$0.25$12.501M128K
opencode$10.00$50.00$0.25$12.501M128K
openrouter$10.00$50.00$0.25$12.501M128K
requesty$10.00$50.00$0.25$12.501M128K
vercel$10.00$50.00$0.25$12.501M128K
vertex_ai-anthropic_models$10.00$50.00$0.25$12.501M128K2027-03-01
vivgrid$10.00$50.00$0.50$12.501M128K
databricks$10.0001$50.00$0.25$12.501M128K
amazon-bedrock · us$11.00$55.00$0.275$13.751M128K
bedrock_converse · eu$11.00$55.00$0.275$13.751M128K
bedrock_converse · us$11.00$55.00$0.275$13.751M128K
bedrock$12.00$60.00$0.30$15.001M128K
venice$12.00$60.00$0.30$15.001M128K

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02openrouterCache read$0.25
2026-09-06openrouterCache read$0.25
2026-09-02openrouterCache write$12.50
2026-09-06openrouterCache write$12.50
2026-09-02openrouterInput$10.00
2026-09-06openrouterInput$10.00
2026-09-02openrouterOutput$50.00
2026-09-06openrouterOutput$50.00

Other listings of this model

same model, different key

More from Anthropic

most-hosted first