The llm CLI tool version 0.32a2 has been released, adding support for OpenAI's /v1/responses endpoint to enable interleaved reasoning for GPT-5 class models.
# Release: llm 0.32a2
Source: [https://simonwillison.net/2026/May/12/llm/](https://simonwillison.net/2026/May/12/llm/)
12th May 2026
Release[llm 0\.32a2](https://github.com/simonw/llm/releases/tag/0.32a2)— Access large language models from the command\-line
A bunch of useful stuff in this[LLM](https://llm.datasette.io/)alpha, but the most important detail is this one:
> Most reasoning\-capable OpenAI models now use the[`/v1/responses`](https://platform.openai.com/docs/api-reference/responses)endpoint instead of`/v1/chat/completions`\. This enables interleaved reasoning across tool calls for GPT\-5 class models\.[\#1435](https://github.com/simonw/llm/pull/1435)
This means you can now see the summarized reasoning tokens when you run prompts against an OpenAI model, displayed in a different color to standard error\. Use the`\-R`or`\-\-hide\-reasoning`flags if you don't want to see that\.
Posted[12th May 2026](https://simonwillison.net/2026/May/12/)at 5:45 pm
## Recent articles
- [Notes on the xAI/Anthropic data center deal](https://simonwillison.net/2026/May/7/xai-anthropic/)\- 7th May 2026
- [Live blog: Code w/ Claude 2026](https://simonwillison.net/2026/May/6/code-w-claude-2026/)\- 6th May 2026
- [Vibe coding and agentic engineering are getting closer than I'd like](https://simonwillison.net/2026/May/6/vibe-coding-and-agentic-engineering/)\- 6th May 2026
This is a**beat**by Simon Willison, posted on[12th May 2026](https://simonwillison.net/2026/May/12/)\.
[projects528](https://simonwillison.net/tags/projects/)[ai2018](https://simonwillison.net/tags/ai/)[annotated\-release\-notes49](https://simonwillison.net/tags/annotated-release-notes/)[openai419](https://simonwillison.net/tags/openai/)[generative\-ai1786](https://simonwillison.net/tags/generative-ai/)[llms1752](https://simonwillison.net/tags/llms/)[llm599](https://simonwillison.net/tags/llm/)
### 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](https://github.com/sponsors/simonw/)
This article announces the release of version 0.32a0 of the 'llm' command-line tool by Simon Willison, providing a monthly briefing on LLM developments.
LLM 0.32a0 is a major backwards-compatible refactor of the Python library and CLI tool, shifting from simple text prompts to supporting sequences of messages and multi-part responses to better handle modern LLM capabilities like structured JSON and tool use.
vLLM v0.19.1 release - a fast and easy-to-use open-source library for LLM inference and serving with state-of-the-art throughput, supporting 200+ model architectures and diverse hardware including NVIDIA/AMD GPUs and CPUs.