---
title: llm 0.33
link: https://simonwillison.net/2026/Aug/22/llm/
source: simon-willison
published: 2026-08-22T17:01:16Z
updated: 2026-08-22T17:01:16Z
first_seen: 2026-09-02T14:07:29.769486161Z
tags:
- annotated-release-notes
- llm
summary: 'Release: llm 0.33 My highlights from this release: Upgraded to the OpenAI Python library 3.x and switched the HTTP client dependency from httpx to httpx2. #1608, #1631 I shipped a quick 0.32.1 fix for this yesterday, but this is the more comprehensive fix. llm embed and llm embed-multi now accept --key. The Python EmbeddingModel.embed(), EmbeddingModel.embed_multi(), Collection.embed() and Collection.embed_multi() methods accept key= too, passing the resolved per-call key to embedding plugins without changing shared model state. Existing plugins that read self.key continue to work through a compatibility fallback. Thanks, ChrisJr404. #757, #1620 The embedding models now use the same pattern for keys that regular LLM models do. llm prompt -t/--template can now be repeated to combine templates in order. This allows model configuration and options from one template to be used with a prompt from another. This unlocks a neat pattern where you can create templates that package a model with a set of default options: llm -m gpt-5.6-luna -o reasoning_effort high --save lhigh llm "Generate an SVG of a pelican riding a bicycle" --save pelican # Combine and run the templates llm -t lhigh -t pelican Reasoning-capable Responses API models now support a reasoning_summary option with auto, concise, and detailed values. This can be used with llm openai endpoint --responses. #1600 This is particularly useful for exercising different models that provide their own imitation of the OpenAI Responses API. Tags: annotated-release-notes, llm'
content: feed
html: 2026-08-22-llm-0-33.html
---

**Release:** [llm 0.33](https://github.com/simonw/llm/releases/tag/0.33)

My highlights from this release:

> - Upgraded to the OpenAI Python library 3.x and switched the HTTP client dependency from `httpx` to `httpx2`. [#1608](https://github.com/simonw/llm/issues/1608), [#1631](https://github.com/simonw/llm/pull/1631)

I shipped a quick [0.32.1 fix](https://simonwillison.net/2026/Aug/21/llm/) for this yesterday, but this is the more comprehensive fix.

> - `llm embed` and `llm embed-multi` now accept `--key`. The Python `EmbeddingModel.embed()`, `EmbeddingModel.embed_multi()`, `Collection.embed()` and `Collection.embed_multi()` methods accept `key=` too, passing the resolved per-call key to embedding plugins without changing shared model state. Existing plugins that read `self.key` continue to work through a compatibility fallback. Thanks, [ChrisJr404](https://github.com/ChrisJr404). [#757](https://github.com/simonw/llm/issues/757), [#1620](https://github.com/simonw/llm/pull/1620)

The embedding models now use the same pattern for keys that regular LLM models do.

> - `llm prompt -t/--template` can now be repeated to combine templates in order. This allows model configuration and options from one template to be used with a prompt from another.

This unlocks a neat pattern where you can create templates that package a model with a set of default options:

```
llm -m gpt-5.6-luna -o reasoning_effort high --save lhigh
llm "Generate an SVG of a pelican riding a bicycle" --save pelican
# Combine and run the templates
llm -t lhigh -t pelican
```

> - Reasoning-capable Responses API models now support a `reasoning_summary` option with `auto`, `concise`, and `detailed` values. This can be used with [llm openai endpoint --responses](https://llm.datasette.io/en/stable/other-models.html#openai-endpoint). [#1600](https://github.com/simonw/llm/issues/1600)

This is particularly useful for exercising different models that provide their own imitation of the OpenAI Responses API.

Tags: [annotated-release-notes](https://simonwillison.net/tags/annotated-release-notes), [llm](https://simonwillison.net/tags/llm)