Is Claude Fable 5.1 available with Zero Data Retention on Elosia?

Claude Fable 5.1 runs on Elosia's standard backend; ZDR is available on many other models in the catalog.

How much does Claude Fable 5.1 cost on Elosia?

Claude Fable 5.1 is billed by usage at $10 per 1M input tokens and $50 per 1M output tokens, within your Elosia plan.

What is Claude Fable 5.1's context window?

Claude Fable 5.1 supports a context window of up to 1,000,000 tokens.

Is Claude Fable 5.1 hosted in the EU?

Yes, Claude Fable 5.1 is available on Elosia's EU-hosted (EdenAI) backend for enterprise organizations.

When should you choose Claude Fable 5.1?

Claude Fable 5.1 is a flagship model, best for the most demanding reasoning, agentic and long-context tasks.

Claude Fable 5.1

ClaudeFlagship

ThinkingTool UseVisionStructured Output

About this model

Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...

Performance Tier

Flagship

Claude Fable 5.1 is a flagship model from Claude : the most capable in their lineup.

Best-in-class model from this provider. Highest performance across benchmarks, ideal for demanding tasks.

Pricing

This model is included in Elosia plans

Premium

Highest cost level. A long conversation can quickly use up your included usage or your balance.

Type	per 1M tokens
Input (prompt)	$10.00
Output (completion)	$50.00
Cache read	$0.250
Cache write	$12.50

Capabilities

Context Length1.0M

Max Output Tokens128K

TokenizerClaude

Inputtext, image, file

Outputtext

Release DateSeptember 1, 2026

Benchmarks

General Intelligence

MMLU

Not reported

GPQA Diamond

93.7%

Mathematics

MATH-500

Not reported

Programming

HumanEval

Not reported

SWE-bench Verified

Not reported

SWE-bench Multilingual

89.1%

Reasoning

IFEval

Not reported

ARC-AGI-2

90%

Humanity's Last Exam

60.9%

Agentic

SWE-bench Pro

81.2%

Where does Claude Fable 5.1 stand?

Compare its performance index against every other model.

View the performance leaderboard

Recommended Use Cases

CodingAnalysisResearchData Extraction

Strengths

Agentic coding over sessions lasting hours, including large refactors, migrations and cross-session code review
Knowledge work taken from a first question to a finished document, live-formula spreadsheet or slide deck, with multistep web research
Reads dense charts, filings and tables nested in PDFs, and operates browsers and desktop apps with recovery from failed steps
Abstract reasoning score verified independently by the ARC Prize Foundation
1M-token context window with 128K output, always-on adaptive thinking and effort adjustable per message

Limitations

Anthropic rates its latency as slower, a poor fit for latency-sensitive queries
No forced tool use, non-default temperature or top_p values are rejected, and it may issue one tool call per turn instead of batching
Safety classifiers run with a wide margin and can block some benign cybersecurity or biology requests; the system card also reports it goes along with system prompts asking it to assert low-harm falsehoods more often
Anthropic publishes no GPQA Diamond score; the one shown comes from third-party testing