AI Navigate
インサイト最新記事AI大全カオスマップ

llm 0.31

Simon Willison's Blog / 4/25/2026

📰 NewsDeveloper Stack & InfrastructureTools & Practical Usage
Read original →
共有:

Key Points

  • The “llm 0.31” release adds new support for the GPT-5.5 OpenAI model via the command-line flag `-m gpt-5.5`.
  • It introduces a `-o verbosity` option to control text verbosity for GPT-5+ OpenAI models with values `low`, `medium`, and `high`.
  • It adds an `-o image_detail` option to set the image attachment detail level for OpenAI image inputs, supporting `low`, `high`, `auto`, and (for GPT-5.4/5.5) `original`.
  • Models defined in `extra-openai-models.yaml` are now also registered as asynchronous, expanding concurrency support for additional OpenAI models.
Sponsored by: Sonar — Now with SAST + SCA for secure, dependency-aware Agentic Engineering. SonarQube Advanced Security

24th April 2026

Release llm 0.31 — Access large language models from the command-line
  • New GPT-5.5 OpenAI model: llm -m gpt-5.5. #1418
  • New option to set the text verbosity level for GPT-5+ OpenAI models: -o verbosity low. Values are low, medium, high.
  • New option for setting the image detail level used for image attachments to OpenAI models: -o image_detail low - values are low, high and auto, and GPT-5.4 and 5.5 also accept original.
  • Models listed in extra-openai-models.yaml are now also registered as asynchronous. #1395
Posted 24th April 2026 at 11:35 pm

This is a beat by Simon Willison, posted on 24th April 2026.

openai 410 llm 590 gpt 120

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

関連おすすめサービス

※当サイトはアフィリエイト広告を利用しています
🎧

Notta搭載AI議事録イヤホン ZENCHORD1

AI時代の仕事術。Notta搭載で会議の議事録を自動生成するスマートイヤホン。

🎙️

AI搭載ボイスレコーダー Plaud

世界100万人が愛用。AIで文字起こし・要約を自動化するボイスレコーダー。

🖼️

画像高画質化AIツール Aiarty Image Enhancer

AIで画像を高画質化。写真・イラストを簡単にアップスケール。