Release: llm 0.32rc2

Simon Willison's LLM command-line tool gained a shortcut for trying services that implement an OpenAI-compatible interface. In version 0.32rc2, the llm openai endpoint command can send prompts, conduct chats and list models without first creating a model configuration. That removes a setup step when testing a new endpoint. Willison says these calls are not recorded in LLM's own logs; the statement concerns the tool's logging, not the remote service's retention practices.

“Luna is a much better and more recent model, albeit slightly more expensive - $0.20 per million input tokens and $1.20 per million output tokens, compared to $0.15/$0.60 for 4o mini.”

“New llm openai endpoint command for running prompts, chats and model listings against arbitrary OpenAI-compatible endpoints without first configuring a model.”

“I got frustrated at the lack of an obvious CLI tool for trying out prompts against arbitrary OpenAI Chat Completions imitation endpoints, so I decided to add that to LLM itself.”