Claude Fable 5.1
Claude Fable 5.1Rankingat high effort?
Full ranking →Alternatives?
CheaperClaude Opus 5.5xhigh+3%-12%$3.46No forced tool use+5
OpenMiMo v2.6 Prothinking-12%-97%$0.13Pass back reasoning_content+3Lower effortSame modelmedium-4%-24%$2.98
CheaperGemini 4 Argonhigh+2%-49%*$1.99Synchronous output stops at 65,536+2
CheaperGPT-6 Astramax-2%-17%$3.26Monitoring can return HTTP 403+2Claude Opus 5.5xhigh+3%-12%$3.46No forced tool use+5Gemini 4 Argonhigh+2%-49%*$1.99Synchronous output stops at 65,536+2GPT-6 Astramax-2%-17%$3.26Monitoring can return HTTP 403+2GPT-6.1 Solmax-5%-81%$0.72Remove unsupported parameters+5Claude Opus 5high-6%-8%$3.61Claude Opus 5.5max+10%+53%$5.98No forced tool use+5MiMo v2.6 ProthinkingOpen-12%-97%$0.13Pass back reasoning_content+3
Kimi K3maxOpen-16%-49%$2.00Sampling parameters are fixed+3
Step 5 PreviewthinkingOpen-17%-74%$1.03web_search not available · Chat Completions+2
Muse Spark OpenxhighOpen-22%-78%$0.84Reasoning off leaves output unchanged · Self-hosted / llama.cpp+1
DeepSeek V4.1 Flash 1017maxOpen-23%-93%$0.26Pass back reasoning_content · Chat Completions+4Claude Opus 5.5highsame-53%$1.82No forced tool use+5Claude Fable 5maxsame+124%$8.75Claude Opus 5high-6%-8%$3.61Claude Opus 4.8max-13%+4%$4.08Claude Sonnet 5.5high-18%-77%$0.88No forced tool use+5Claude Haiku 5.5high-33%-98%$0.079Remove sampling parameters+5Claude Sonnet 5high-36%-54%$1.79Claude Opus 4.7high-40%—$5 / $25All Anthropic models →History
2 versionsBenchmarks
in Chat & KnowledgeWatch out 6
Replace forced tool_choice›
Forced tool_choice returns HTTP 400; use auto with an explicit instruction and strict tools, or JSON outputs. Source ↗
Adaptive thinking is always on›
Disabled thinking or manual budget_tokens returns HTTP 400; omit thinking or use adaptive thinking. Source ↗
No non-default sampling values›
Non-default temperature, top_p or top_k returns HTTP 400; omit non-default sampling values. Source ↗
Requires 30-day data retention · Claude API›
A Claude API organization or workspace without 30-day retention receives HTTP 400; configure workspace retention or contact the Anthropic account team. Source ↗
Thinking blocks bind to conversations›
Where conversation binding is enforced, replaying an invalidated block returns HTTP 400; use the documented drop_block control to continue without it. Source ↗
No assistant prefill›
Assistant prefill returns HTTP 400; use system prompt instructions instead. Source ↗
FAQ
How much does Claude Fable 5.1 cost?›
$10 per 1M input tokens and $50 per 1M output tokens; cached input $0.25 per 1M. A typical benchmark task costs about $3.91 at high effort.
Is Claude Fable 5.1 free to use?›
There is no free API; the cheapest paid price is $10 per 1M input tokens.
How good is Claude Fable 5.1, and what is it best at?›
#3 of 334 in Chat & Knowledge, #7 of 132 in Coding, #30 of 133 in Agents & Tool Use, #7 of 195 in Writing & Language, #5 of 37 in Vision & Documents. Strongest at: Coding, Agents & work tasks, Reasoning, Science, Long context, Knowledge.
Is Claude Fable 5.1 better than Claude Fable 5?›
On Humanity's Last Exam, Claude Fable 5.1 scores 59.1 vs 55.5 — higher. It is 55% cheaper per task.
How can I use Claude Fable 5.1?›
Through the API of Amazon Bedrock, Anthropic, Azure, Google.
What is the context window of Claude Fable 5.1?›
1M tokens, with up to 128K output tokens.
When was Claude Fable 5.1 released? Is there a newer version?›
Released 2026-09-01. It is the current version in its line.
Is Claude Fable 5.1 open source?›
No, Claude Fable 5.1 is a closed model available through an API. The closest open-weights option here is MiMo v2.6 Pro.
Can Claude Fable 5.1 read images?›
It accepts text and images, PDF files as input.
What is Claude Fable 5.1?›
Claude Fable 5.1 is a closed language model from Anthropic, released Sep 2026, the successor to Claude Fable 5.
What are the best alternatives to Claude Fable 5.1?›
Claude Opus 5.5 (cheaper), MiMo v2.6 Pro (open weights).