Setting a custom price for a model in AgentsView

Simon Willison's Blog Tools
agentsview custom-pricing token-usage claude-fable-5 wes-mckinney cost-analysis python-toolkit

Summary

Simon Willison explains how to set a custom price for a model (e.g., Claude Fable 5) in the AgentsView Python toolkit, which is used for analyzing coding agent token usage and costs.

No content available
Original Article
View Cached Full Text

Cached at: 06/10/26, 12:26 AM

# TIL: Setting a custom price for a model in AgentsView Source: [https://simonwillison.net/2026/Jun/9/agentsview-custom-model-price/](https://simonwillison.net/2026/Jun/9/agentsview-custom-model-price/) [TIL](https://simonwillison.net/elsewhere/til/)[Setting a custom price for a model in AgentsView](https://til.simonwillison.net/llms/agentsview-custom-model-price)— I'm a recent convent to AgentsView, Wes McKinney's \(previously of Pandas fame\) Python toolkit for analyzing transcripts of coding agents from your own computer\. I've been really enjoying[AgentsView](https://agentsview.io/)by Wes McKinney as a tool for exploring my token usage across different coding agents running on my laptop\. Claude Fable 5 came out today and wasn't yet included in the pricing database AgentsView uses\. I used Fable to reverse\-engineer AgentsView and figured out this recipe for setting custom prices\. Here's my Claude Fable 5 usage for today so far, plotted by AgentsView as a treemap across my different local projects: ![Screenshot of a cost analytics dashboard. Cost Attribution - Click to hide from chart - toggle buttons for Project / Model / Agent and Treemap / List. A treemap shows a large red block: prod_datasette_agent $74.06 89.3%, then blue: cloud $3.98 4.8%, teal: datasette $2.81 3.4%, pink: money $1.92 2.3%, and a thin orange sliver. A legend lists 1 prod_datasette_agent $74.06, 2 cloud $3.98, 3 datasette $2.81, 4 money $1.92, 5 simon $0.15. Below left, Top Sessions by Cost: 1 Claude - Review ./datasette-agent and ./datasette-apps - we are going to a... - prod_datasette_agent · 08a1f374-0e77-420f-be2d-af805d67e8aa - 55.9M $74.06; 2 Claude - issues.db is a copy of the Datasette issues database. There are a... - datasette · 8caa2d2d-b91f-43b3-bf3a-4268995b6011 - 826.8k $2.81; 3 Claude - Consult fly-docs and then look at datasette.cloud (which launche... - cloud · bfcacc70-09d7-4b27-aaec-4bb8accd9fec - 924.7k $2.61; 4 Claude - simonwillisonblog.db is a copy of my blog, plus all my software re... - money · 0c0fb9dc-6347-4e1b-9307-3709a7cdf0c8 - 542.9k $1.92; 5 Claude - Look in datasette.cloud and figure out all remaining steps and dec... - cloud · 45963b5f-608a-4caa-ad6b-6ae81e1dbf0d - 455k $1.37; 6 Claude - simon - simon · deeccb5d-9e90-4b1e-bfe6-c2b271e1b1d4 - 26.4k $0.15. Below right, Cache Efficiency with horizontal bars: Cache Reads 57.6M (nearly full green bar), Cache Writes 769.3K, Uncached Input 64.4K, Output 300.9K (all tiny bars), and a green highlighted note: $516.62 saved vs uncached.](https://static.simonwillison.net/static/2026/agentsview-fable.jpg)

Similar Articles

Fable's judgement

Simon Willison's Blog

A practical tip from Simon Willison: allow Claude Code's Fable model to use its own judgment for testing and delegate coding tasks to subagents running cheaper models, reducing token usage while maintaining quality.