← Model list

Claude Fable 5

anthropic·anthropic/claude-fable-5·BETA·Closed·claude-fable series·NEW

Claude model for creative writing, analysis, and controlled agent workflows

At a glance
Official price$10.00 / $50.00 per 1M
Cache read $1.00 · Anthropic
Lowest paid$3.00 / $18.50
Xpersona Gateway · 4× spread
1 more $0 channels
Context1,000,000
Output limit128,000
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
Modalities
TextImagePDF
Knowledge cutoff2026-01-31
Released / updated2026-06-09 / 2026-06-09

Quality & performanceArtificial Analysis · Intelligence Index v4.1 · rep. tier Adaptive Reasoning, Max Effort, Opus 4.8 Fallback

Intelligence62.1
Value9
Coding76.5
Agentic56.6
Output speed67 tok/s
TTFT148.12 s
Cost per task$3.1396
Value formulaIQ 62.1 ÷ min blended $6.875 = 9

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 31 providers28 with public prices · 1 free

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
KenariGatewayFree1,000,000128,000
XpersonaGateway$3.00$18.50$0.301,000,000128,000
RequestyGateway$9.00$45.00$0.90$11.251,000,000128,000
NanoGPTGateway$10.00$50.00$1.00$12.501,000,000128,000
ImpossiblGateway$10.00$50.00$1.00$12.501,000,000128,000
OpenRouterGateway$10.00$50.00$1.00$12.501,000,000128,000
CrossModelGateway$10.00$50.00$1.00$12.501,000,000128,000
AnthropicOfficialFirst-party$10.00$50.00$1.00$12.501,000,000128,000
Amazon Bedrock
anthropic.claude-fable-5
Cloud$10.00$50.00$1.00$12.501,000,000128,000
Merge GatewayGateway$10.00$50.00$1.00$12.501,000,000128,000

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

1Xpersona$1,201.00
2Requesty$3,078.00
3NanoGPT$3,420.00
4Impossibl$3,420.00
5OpenRouter$3,420.00
6CrossModel$3,420.00
7Anthropic · Official$3,420.00

1 more channels offer $0 (Kenari); free tiers usually have rate limits and no SLA, excluded from ranking.

Switch to Xpersona to save $2,219.00/mo (65%)
Note: this is a gateway; verify availability and rate limits yourself.

Benchmark9 items

NameConditionsScoreMetricSource
SWE-Bench Pro80.3resolve rateSource ↗
SWE-Bench Verified95resolvedSource ↗
Terminal-Benchv2.188success rateSource ↗
Humanity's Last Examvariant: no tools59accuracySource ↗
Humanity's Last Examvariant: with tools64.5accuracySource ↗
OSWorld-Verified85success rateSource ↗
FrontierCodevariant: high effort · dataset: Diamond29.3pass rateSource ↗
GDPval-AA1932EloSource ↗
AutomationBench17.4success rateSource ↗

The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.

Reasoning control

effort = loweffort = mediumeffort = higheffort = xhigheffort = maxeffort = nonebudget_tokensToggle (on / off)

2 / 31 providers expose no reasoning control (reasoning_options: []).

Related models

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$50.00$02026-08-052026-08-132026-08-05 · Input list $10.002026-08-06 · Input list $10.002026-08-07 · Input list $10.002026-08-08 · Input list $10.002026-08-09 · Input list $10.002026-08-10 · Input list $10.002026-08-11 · Input list $10.002026-08-12 · Input list $10.002026-08-13 · Input list $10.002026-08-05 · Output list $50.002026-08-06 · Output list $50.002026-08-07 · Output list $50.002026-08-08 · Output list $50.002026-08-09 · Output list $50.002026-08-10 · Output list $50.002026-08-11 · Output list $50.002026-08-12 · Output list $50.002026-08-13 · Output list $50.002026-08-05 · Min blended $6.882026-08-06 · Min blended $6.882026-08-07 · Min blended $6.882026-08-08 · Min blended $6.882026-08-09 · Min blended $6.882026-08-10 · Min blended $6.882026-08-11 · Min blended $6.882026-08-12 · Min blended $6.882026-08-13 · Min blended $6.88