Subject: Local AI Liberty: Why block custom OpenAI-compatible models?
Message: Hi team. I'm a user running Clawdbot (v2026.1.24-3) on WSL2, connecting to a local LM Studio (RTX 5060 Ti).
My setup is 100% correct, and curl confirms the model is responding perfectly. However, Clawdbot throws an Unknown model error just because I'm using a local model name: openai/openai-gpt-oss-20b-abliterated-uncensored-neo-imatrix.
In an open-source automation tool, it feels like an absurd limitation to hardcode allowed model IDs and block local OpenAI-compatible endpoints that don't match your internal list.
Can we get a fix to allow ANY model ID when a custom baseUrl is provided? Local AI users need this freedom.
My setup is 100% correct, and curl confirms the model is responding perfectly. However, Clawdbot throws an Unknown model error just because I'm using a local model name: openai/openai-gpt-oss-20b-abliterated-uncensored-neo-imatrix.
In an open-source automation tool, it feels like an absurd limitation to hardcode allowed model IDs and block local OpenAI-compatible endpoints that don't match your internal list.
Can we get a fix to allow ANY model ID when a custom baseUrl is provided? Local AI users need this freedom.
The AI that actually does things. Emails, calendar, home automation - all from your favorite chat app. New shell, ready to help. The lobster way.
83,815Members
Resources
Recent Announcements
Similar Threads
Was this page helpful?
