Claude Fable 5
Claude Fable 5Alternatives?
CheaperClaude Opus 5.5maxwins 74%-60%$5.98No forced tool use+5
BetterGPT-6.1 Solmaxwins 68%-80%$0.72Remove unsupported parameters+5
OpenDeepSeek V4.1 Flash 1017maxwins 56%-97%$0.30 / $1.20Pass back reasoning_content · Chat Completions+4CheaperClaude Sonnet 5.5xhighwins 70%-80%$2.01No forced tool use+5CheaperClaude Opus 5maxwins 59%-50%$5.86Claude Opus 5.5maxwins 74%-60%$5.98No forced tool use+5Claude Sonnet 5.5xhighwins 70%-80%$2.01No forced tool use+5GPT-6.1 Solmaxwins 68%-80%$0.72Remove unsupported parameters+5Claude Opus 5maxwins 59%-50%$5.86GPT-6 Solmaxwins 58%-80%$1.04GPT-6.1 Solmaxwins 68%-80%$0.72Remove unsupported parameters+5Claude Sonnet 5.5highwins 62%-80%$0.88No forced tool use+5GPT-6 Solmaxwins 58%-80%$1.04
Muse Spark 1.3maxwins 55%-90%$1.60Only auto tool_choice is supported+5
Gemini 4 Argonhighwins 58%-80%*$1.99Synchronous output stops at 65,536+2DeepSeek V4.1 Flash 1017maxOpenwins 56%-97%$0.30 / $1.20Pass back reasoning_content · Chat Completions+4
Kimi K3maxOpenwins 54%-70%$2.00Sampling parameters are fixed+3
MiMo v2.6 FlashunstatedOpensame-99%$0.14 / $0.28Pass back reasoning_content+3
Hy4 previewOpensame-94%$0.83 / $2.50No image input
Qwen3.8 FlashunstatedOpensame-99%$0.15 / $0.47Context: 1M → 262K+6Claude Opus 5.5maxwins 74%—$5.98No forced tool use+5Claude Fable 5.1maxwins 66%—$7.63Replace forced tool_choice+5Claude Sonnet 5.5highwins 62%—$0.88No forced tool use+5Claude Opus 5highwins 55%—$3.61Claude Haiku 5.5highwins 45%—$0.079Remove sampling parameters+5Claude Opus 4.7highwins 41%—$5 / $25Claude Opus 4.8highwins 40%—$5 / $25Claude Opus 4.6highwins 39%—$5 / $25All Anthropic models →History
2 versionsBenchmarks
in CodingFAQ
How much does Claude Fable 5 cost?›
$10 per 1M input tokens and $50 per 1M output tokens; cached input $1 per 1M.
Is Claude Fable 5 free to use?›
There is no free API; the cheapest paid price is $10 per 1M input tokens.
How good is Claude Fable 5, and what is it best at?›
#4 of 334 in Chat & Knowledge, #11 of 132 in Coding, #31 of 133 in Agents & Tool Use, #3 of 195 in Writing & Language, #8 of 37 in Vision & Documents. Strongest at: Coding, Agents & work tasks, Tool calling, Reasoning, Science, Long context, Knowledge.
Is Claude Fable 5 better than MiMo v2.6 Pro?›
On WebDev Arena, Claude Fable 5 scores 1,624 vs 1,625 — about the same.
How can I use Claude Fable 5?›
Through the API of Amazon Bedrock, Anthropic, Azure, Claude Platform on AWS, DeepInfra and 1 more.
What is the context window of Claude Fable 5?›
1M tokens, with up to 128K output tokens.
When was Claude Fable 5 released? Is there a newer version?›
Released 2026-06-07. It has been superseded by Claude Fable 5.1.
Is Claude Fable 5 open source?›
No, Claude Fable 5 is a closed model available through an API. The closest open-weights option here is DeepSeek V4.1 Flash 1017.
Can Claude Fable 5 read images?›
It accepts text and images, PDF files as input.
What is Claude Fable 5?›
Claude Fable 5 is a closed language model from Anthropic, released Jun 2026.
What are the best alternatives to Claude Fable 5?›
Claude Opus 5.5 (cheaper), GPT-6.1 Sol (better), DeepSeek V4.1 Flash 1017 (open weights).