datasette-llm-usage 0.2a0
<p><strong>Release:</strong> <a href="https://github.com/datasette/datasette-llm-usage/releases/tag/0.2a0">datasette-llm-usage 0.2a0</a></p> <blockquote> <ul> <li>Removed features relating to allowances and estimated pricing. These are now the domain of <a href="https://github.com/datasette/datasette-llm-accountant">datasette-llm-accountant</a>.</li> <li>Now depends on <a href="https://github.com/datasette/datasette-llm">datasette-llm</a> for model configuration. <a href="https://github.com/datasette/datasette-llm-usage/pull/3">#3</a></li> <li>Full prompts and responses and tool calls can now be logged to the<code>llm_usage_prompt_log</code> table in the internal database if you set the new <code>datasette-llm-usage.log_prompts</code> plugin configuration setting.</li> <li>Redesigned the <
Removed features relating to allowances and estimated pricing. These are now the domain of datasette-llm-accountant.
Now depends on datasette-llm for model configuration. #3
Full prompts and responses and tool calls can now be logged to the llm_usage_prompt_log table in the internal database if you set the new datasette-llm-usage.log_prompts plugin configuration setting.
Redesigned the /-/llm-usage-simple-prompt page, which now requires the llm-usage-simple-prompt permission.
Simon Willison Blog
https://simonwillison.net/2026/Apr/1/datasette-llm-usage/#atom-everythingSign in to highlight and annotate this article
Conversation starters
Daily AI Digest
Get the top 5 AI stories delivered to your inbox every morning.
More about
modelreleasefeature
AI Central in US-Iran 2026 War as Targeting Systems Speed Strikes but Spark Accuracy and Ethics
Artificial intelligence has emerged as a defining feature of the ongoing U.S.-Israeli military campaign against Iran, enabling rapid targeting and a high tempo of strikes that military officials describe as unprecedented, though questions persist about the technology's precision and the human costs involved.
Cortex Code in Snowflake: How to Use It Without Burning Credits
Snowflake Cortex Code (CoCo) is like an AI assistant inside Snowsight (and CLI also). You can ask it to write SQL, create dbt models, explore data, help in ML work, and even do some admin tasks. But one thing people don’t realise early — this tool is powerful, but also costly if used wrongly. Bad prompts → more tokens → more credits → surprise bill. Prompt Engineering (this directly impacts cost) CoCo works on token consumption. what you type → counted 2. what it replies → counted If your prompt is vague → more tool calls → more cost. Example: Bad: Help me with my data Good: Create staging model for RAW.SALES.ORDERS with not_null on ORDER_ID Best Practices: Use full table names 2. Be clear about output 3. Keep prompts small 4. Provide business logic upfront 5. Use AGENTS.md for consistency
The Stack Nobody Recommended
The most common question I got after publishing Part 1 was some variation of "why did you pick X instead of Y?" So this post is about that. Every major technology choice, what I actually considered, where I was right, and where I got lucky. I'll be upfront: some of these were informed decisions. Some were "I already know this tool, and I need to move fast." Both are valid, but they lead to different trade-offs down the line. The Backend: FastAPI I come from JavaScript and TypeScript. Years of React on the frontend, Express and Fastify on the backend. When I decided this project would be Python, because that's where the AI/ML ecosystem lives, I needed something that didn't feel foreign. FastAPI clicked immediately. The async/await model, the decorator-based routing, and type hints that actu
Knowledge Map
Connected Articles — Knowledge Graph
This article is connected to other articles through shared AI topics and tags.
Discussion
Sign in to join the discussion
No comments yet — be the first to share your thoughts!