Initial impressions of Claude Fable 5

Simon Willison’s Weblog

Subscribe

Sponsored by: AWS — If you're building with AI, AWS Summit NYC on June 17 is the room you want to be in. 200+ sessions. Totally free. Register here

Initial impressions of Claude Fable 5

9th June 2026

I didn’t have early access to today’s Claude Fable 5 release, but I’ve spent the past ~5.5 hours putting it through its paces. My initial impressions are that this is something of a beast. It’s slow, expensive and has been quite happily churning through everything I’ve thrown at it so far. As is frequently the case with current frontier models the challenge is finding tasks that it can’t do.

First, let’s review the key characteristics.

Anthropic claim that Claude Fable 5 offers the same performance as Claude Mythos 5, except with much more strict guardrails in place to prevent it being used for harmful things. Those guardrails trigger often enough that the Claude API has new mechanisms for letting you know when you hit them, and even has a new option to request it falls back to another model automatically if something gets rejected.

Claude Mythos 5 is out today as well, Anthropic say it “Shares Claude Fable 5’s capabilities without the safety classifiers”.

The models have a 1 million token context window, 128,000 maximum output tokens and a knowledge cut-off date of January 2026.

They are priced at twice the price of Claude Opus 4.5/4.6/4.7/4.8: $10/million input tokens and $50/million output tokens. There’s no increase in price for longer context usage.

Other than that the upgrade guide is substantially thinner than the similar guide for Opus 4.8.

The big model smell

The best way to describe Fable is that it feels big. Not just in terms of speed and cost, but also in how much it knows.

Here’s an example prompt, which I used to compare Fable’s knowledge with Opus 4.8 (typo included):

List all of Simon Willion's open source projects, most recent first, each with a rough date of when they were first released

Opus 4.8’s reply started like this:

I don’t have a reliable, comprehensive, and date-verified list of all of Simon Willison’s open source projects, and I want to be honest about that rather than risk giving you inaccurate dates or fabricated entries.

Here’s what I can tell you with reasonable confidence:

Well-known projects by Simon Willison:

LLM (~2023) – A command-line tool and Python library for interacting with large language models.

Datasette (~2017) – A tool for exploring and publishing data, probably his most prominent recent project.

sqlite-utils (~2018-2019) – A Python library and CLI tool for manipulating SQLite databases, often used alongside Datasette.

Django (2005) – He is one of the co-creators of the Django web framework, along with Adrian Holovaty, originally developed at the Lawrence Journal-World newspaper.

He also maintains a large ecosystem of Datasette plugins and many smaller utilities (often with names like shot-scraper, various *-to-sqlite tools for importing data, etc.).

That’s not bad. Here’s the start of the response for the exact same prompt from Fable 5—both models were running without access to search:

I think you mean Simon Willison — the prolific open source developer, co-creator of Django, and creator of Datasette.

An important caveat upfront: a truly complete list isn’t feasible. Simon Willison is famously prolific — he has published hundreds of repositories (Datasette alone has 100+ plugins, many written by him), and my knowledge has a cutoff date, so I’ll be missing his most recent work. Below are his notable projects with approximate initial release dates, most recent first:

Notable projects (approximate dates)

files-to-prompt (April 2024) – concatenates files into a single prompt for LLMs

datasette-extract (2024) – plugin for extracting structured data using LLMs

LLM (May–June 2023) – CLI tool and Python library for interacting with large language models, plus a large ecosystem of plugins (llm-gpt4all, llm-mistral, llm-claude, etc., 2023 onward)

symbex (June 2023) – search Python code for symbols

ttok and strip-tags (May 2023) – CLI tools for token counting and HTML cleanup for LLM pipelines

datasette-lite (May 2022) – Datasette running entirely in the browser via WebAssembly/Pyodide

shot-scraper (March 2022) – automated website screenshots via Playwright

s3-credentials (November 2021) – CLI for creating scoped AWS S3 credentials

django-sql-dashboard (2021) – SQL reporting dashboards for Django

Dogsheep suite (2019) – personal analytics tools: twitter-to-sqlite, github-to-sqlite, healthkit-to-sqlite, dogsheep-beta, etc.

sqlite-utils (2018) – CLI and Python library for manipulating SQLite databases

Datasette (November 2017) – his flagship project; tool for exploring and publishing data

csvs-to-sqlite (2017) – convert CSV files to SQLite

Various early tools (~2007–2010) – soupselect, json-head, geocoders, and others

Django (developed 2003–2005, open-sourced...