Initial impressions of Claude Fable 5

Initial impressions of Claude Fable 5

Simon Willison’s Weblog

Subscribe

#smallhead

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 July 2005) – co-created with Adrian Holovaty at the Lawrence Journal-World

(Here’s GPT-5.5 for good measure . It listed even more projects than Fable did!)

In the past I’ve stated that I don’t care about how much models know —I want them to be able to manipulate text and code in useful ways and actively look up the information they need via search tools, not bake it into their weights.

But knowledge like this is a reasonably good proxy for model size—you can cram a whole lot more details about the world into a larger number of parameters.

Does knowing more stuff mean the model is better at the tasks we pose to it? I can certainly imagine how a coding model with deeper knowledge of modern libraries and patterns could crunch through coding tasks more effectively.

Is Fable really bigger than Opus? Anthropic haven’t said anything about model size, so all we have are tea-leaves, but the speed, pricing and my own poking at its knowledge make me think that it’s a large model. Maybe the largest yet from any vendor.

#### Using Fable in Claude.ai

Anthropic made Fable 5 available across all of their surfaces—the Claude.ai chat interface, Claude Code for web, Claude Code CLI and Claude Cowork as well. The model is available “until June 22nd” on the subscription plans (I’m on $100/month Max at the moment), after which it will be billed extra.

Claude.ai is often under-estimated. Since September 2025 every chat has had access to a full container environment to run code, including the ability to install additional packages and even clone repositories directly from GitHub.

Last week I released micropython-wasm , a Python library that uses wasmtime to run a custom build of MicroPython in WebAssembly to act as a sandbox for untrusted Python code.

I decided to see if Fable could upgrade that to running full Python instead. I started with this prompt:

Clone simonw/micropython-wasm from GitHub and research how this could use a full Python as opposed to MicroPython

Fable identified that it could use Brett Cannon’s cpython-wasi-build builds for this, but was unable to download them itself due to environment restrictions.

So I grabbed the two zip files from that page and uploaded them to Claude:

Here's the Brett Cannon builds ( python-3.zip , _build-python-3.zip as attachments)

And that was that. It churned away for a few minutes and got the entire thing working.

Part of the response included:

I tried the cleaner single-zip-stdlib approach to shrink the filesystem surface, but CPython’s getpath bootstrap fails to find encodings from inside a zip without more prefix finessing — the directory-preopen approach works reliably, so that’s what the PoC uses. The zip path is solvable but needs _PYTHONHOME /frozen-getpath work.

So I said:

Try a bit more at the single-zip-stdlib problem

Then a little later:

I want a wheel that has the whole system in it, the Python wrappers and the WASM files and the stdlibrary, so I can do uv run --with path-to-whl python -c "demo code"

... and it gave me this 13.9MB cpython_wasm-0.1.0-py3-none-any.whl file. You can try running Python code in a sandbox using that wheel URL and uv like this:

uv run --with https://static.simonwillison.net/static/cors-allow/2026/cpython_wasm-0.1.0-py3-none-any.whl \
  cpython-wasm -c
'
print(45 ** 56)
'

Here’s the full chat transcript .

This was a very strong start.

#### Adding features to Datasette Agent and LLM using Claude Code

Before I’d realized it was Fable day, my stretch goal for today was to add a new feature to Datasette Agent : I wanted tool calls within that agent software to gain the ability to pause mid-execution and request approval directly from the user.

This felt like a suitably meaty task to throw at the new model.

Over the course of the day Fable not only solved that problem , it also identified and then implemented four issues in my underlying LLM library that would help support this kind of advanced pause-resume mechanism in tool calls.

It got everything working first using somewhat gnarly hacks, but the moment I told it that changes to LLM itself were in scope it set to work unraveling the hacks and turning them into supported features of LLM instead.

My stretch goal turned into LLM 0.32a3 , almost entirely written by Fable. Here are the release notes:

Driven by the needs of Datasette Agent ’s human-in-the-loop ask_user() feature, made the following improvements to how tool calls work: Tool implementations can declare a parameter named llm_tool_call in order to be passed the llm.ToolCall object for the current invocation. This allows them to access the current llm_tool_call.tool_call_id . See Accessing the tool call from inside a tool . #1480 Every tool call is now guaranteed a unique tool_call_id —providers that do not supply one get a synthesized tc_ -prefixed ULID. #1481 Tools can raise a llm.PauseChain exception to cleanly pause the tool chain, useful for things like waiting for human approval. The exception propagates to the caller with .tool_call and .tool_results (completed sibling results) attached, and no model call is made with a placeholder result. See Pausing a chain from inside a tool . #1482 Failure semantics for concurrent tool execution: async sibling tool calls always run to completion before a pause or hook exception propagates. #1482 Chains can now resume from a messages= history ending in unresolved tool calls: the calls are executed through the normal before_call / after_call machinery before the first model call, skipping any that already have results. The execute_tool_calls() method also accepts a new optional tool_calls_list= argument for executing an explicit list of ToolCall objects in place of the calls requested by the response. See Resuming a chain with pending tool calls . #1482 Fixed a bug where the async tool executor silently dropped calls to tools not present in tools= —these now return Error: tool "..." does not exist results, matching the sync executor. #1483

I’m really impressed with the quality of API design, tests, code and documentation that Fable put together for this. I spent several hours on it today, but it feels like several days’ worth of work.

#### How much I’ve spent

I recently started using AgentsView to help track my local LLM usage across all of the different coding agents. I published a TIL today about adding custom Fable pricing to that tool, which I expect will not be necessary in the very near future.

After setting the price, I ran this command to start a localhost web server to explore my usage:

uvx agentsview serve

Here’s the treemap showing the breakdown of my Fable usage across various projects today:

I used $110.42 worth of tokens today, all as part of my $100/month subscription.

#### And some pelicans

I ran “Generate an SVG of a pelican riding a bicycle” against all five thinking effort levels with Fable.

Here are the results , including the token cost for each one:

low: 1,929 out, 9.67c

medium: 2,290 out, 11.475c

high: 2,057 out, 10.31c

xhigh: 5,992 out, 29.985c

max: 14,430 out, 72.175c

It’s interesting that high ended up using fewer tokens than medium for this particular run.

Here are the Opus 4.8 pelicans for comparison.

Posted

at 11:59 pm · Follow me on

Mastodon

,

Bluesky

Twitter

or

subscribe to my newsletter

More recent articles

• Running Python code in a sandbox with MicroPython and WASM - 6th June 2026

• Claude Opus 4.8: "a modest but tangible improvement" - 28th May 2026

#primary

This is Initial impressions of Claude Fable 5 by Simon Willison, posted on 9th June 2026 .

ai

2,063

generative-ai

1,821

llms

1,789

anthropic

293

claude

280

llm-pricing

77

pelican-riding-a-bicycle

117

llm-release

204

claude-mythos

9

Previous: Running Python code in a sandbox with MicroPython and WASM

Monthly briefing

Sponsor me for $10/month and get a curated email digest of the month's most important LLM developments.

Pay me to send you less!

Sponsor & subscribe

#secondary

#wrapper

• Disclosures

• Colophon

• ©

• 2002

• 2003

• 2004

• 2005

• 2006

• 2007

• 2008

• 2009

• 2010

• 2011

• 2012

• 2013

• 2014

• 2015

• 2016

• 2017

• 2018

• 2019

• 2020

• 2021

• 2022

• 2023

• 2024

• 2025

• 2026