Title: Release: datasette-llm 0.1a4 | BestBlogs.dev
URL Source: https://www.bestblogs.dev/article/9184aa7a
Published Time: 2026-03-31 21:17:23
Markdown Content: Skip to main content Toggle navigation menu Toggle navigation menuArticlesPodcastsVideosTweetsSourcesNewsletters
⌘K
Change language Switch ThemeSign In
Narrow Mode
Release: datasette-llm 0.1a4
S Simon Willison's Weblog @Simon Willison
One Sentence Summary
Release of datasette-llm 0.1a4 introduces purpose-based API key configuration for specific LLM models and tasks.
Summary
Simon Willison announced the release of datasette-llm 0.1a4, a foundational plugin for integrating Large Language Models (LLMs) into the Datasette ecosystem. The key feature of this update is the ability to configure distinct API keys for different models based on their specific roles, such as assigning a dedicated key for data enrichment tasks. The release also coincides with llm-echo 0.3, a utility updated to support testing for these new configuration capabilities.
Main Points
* 1. Purpose-based API key configuration.Users can now assign specific API keys to models based on their intended use, allowing for better cost tracking and access control for tasks like automated data enrichments. * 2. Foundational plugin architecture.The datasette-llm plugin is designed as a core dependency that other Datasette plugins can leverage to provide LLM-powered features. * 3. Supporting testing utilities.The release of llm-echo 0.3 provides the necessary infrastructure to test custom API key logic and model references.
Metadata
AI Score
80
Website simonwillison.net
Published At Today
Length 68 words (about 1 min)
Sign in to use highlight and note-taking features for a better reading experience. Sign in now
31st March 2026
Releasedatasette-llm 0.1a4— LLM integration plugin for other plugins to depend on
> * Ability to configure different API keys for models based on their purpose - for example, set it up so enrichments always use gpt-5.4-mini with an API key dedicated to that purpose. #4
I released llm-echo 0.3 to provide an API key testing utility I needed for the tests for this new feature.
S Simon Willison's Weblog @Simon Willison
One Sentence Summary
Release of datasette-llm 0.1a4 introduces purpose-based API key configuration for specific LLM models and tasks.
Summary
Simon Willison announced the release of datasette-llm 0.1a4, a foundational plugin for integrating Large Language Models (LLMs) into the Datasette ecosystem. The key feature of this update is the ability to configure distinct API keys for different models based on their specific roles, such as assigning a dedicated key for data enrichment tasks. The release also coincides with llm-echo 0.3, a utility updated to support testing for these new configuration capabilities.
Main Points
* 1. Purpose-based API key configuration.
Users can now assign specific API keys to models based on their intended use, allowing for better cost tracking and access control for tasks like automated data enrichments.
* 2. Foundational plugin architecture.
The datasette-llm plugin is designed as a core dependency that other Datasette plugins can leverage to provide LLM-powered features.
* 3. Supporting testing utilities.
The release of llm-echo 0.3 provides the necessary infrastructure to test custom API key logic and model references.
Key Quotes
* LLM integration plugin for other plugins to depend on * Ability to configure different API keys for models based on their purpose * set it up so enrichments always use gpt-5.4-mini with an API key dedicated to that purpose
AI Score
80
Website simonwillison.net
Published At Today
Length 68 words (about 1 min)
Tags
Datasette
LLM
API Management
Python
Open Source
Related Articles
* My fireside chat about agentic engineering at the Pragmatic Summit * Andrej Karpathy on Code Agents， AutoResearch， and the Loopy Era of AI * First impressions of Claude Cowork， Anthropic’s general agent * 2025: The year in LLMs * OpenAI Launches GPT-5.4 with Native Computer Use and 1M Context * Google DeepMind Launches Gemini 3.1 Pro with 2x Reasoning Performance * OpenAI Launches GPT-5.3-Codex * GPT-5.4 mini and GPT-5.4 nano: 76,000 Photos for $52 * Conversation: LLMs and the what/how loop * Wilson Lin on FastRender: a browser built by thousands of parallel agents HomeArticlesPodcastsVideosTweets