anthropic

Claude Fable 5.1

Claude Fable 5.1 improves on Fable 5 across long-running agentic coding, knowledge work, and research, following instructions precisely over sessions that run unattended for hours.

reasoningtool useexplicit cachingfile inputvisionstructured outputtextimagepdf

Overview

Type: language
Context: 1M
Max output: 128K
Input / output: text, image, pdf / text

API

Model identifier

anthropic/claude-fable-5.1

Providers and live performance

Rolling Gateway metrics. Latency is time to first token; throughput is output tokens per second.

P50 / P95 over the last hour

Provider	Status	Latency	Throughput	Uptime 15m / 1h / 1d	Input	Output	Cache read / write	Discount	Regions	ZDR	No training
anthropic	Operational	2.60s / 4.70s	81.5 / 86.4 tok/s	100.00% / 100.00% / 99.94%	$10.00/M	$50.00/M	$0.25/M / $12.50/M	—	us	No	Yes
bedrock	Operational	2.29s / 4.42s	76.0 / 84.8 tok/s	100.00% / 100.00% / 99.94%	$10.00/M	$50.00/M	$0.25/M / $12.50/M	—	us	No	Yes
vertexAnthropic	Operational	1.56s / 2.66s	82.0 / 85.7 tok/s	100.00% / 100.00% / 100.00%	$10.00/M	$50.00/M	$0.25/M / $12.50/M	—	—	No	Yes

Pricing

input

0.00001

output

0.00005

input cache read

0.00000025

input cache write

0.0000125

web search

regional

{ "us": { "input": "0.000011", "output": "0.000055", "input_cache_read": "0.000000275", "input_cache_write": "0.00001375" } }

Capabilities

reasoningtool useexplicit cachingfile inputvisionstructured outputtextimagepdf

Supported parameters

max tokens

Yes

temperature

Yes

stop

Yes

tools

Yes

tool choice

Yes

reasoning

Yes

include reasoning

Yes

response format

Yes

structured outputs

Yes

Reasoning options

options

{ "type": "effort", "values": [ "low", "medium", "high", "xhigh", "max" ] }

Metadata

type

language

context window

max output

128K

knowledge cutoff

2026-06

released

Aug 31, 2026

temperature control

Yes

zero data retention

none

no training

all

regions

api specifications

v2, v3, v4