Schülerpraktikum beim Deepstate.

Not how tax brackets work, but nevermind...

Anyone found a way to attach files to maple-proxy chat completion requests? Also wondering, where I can find context length limits per model with

I always felt like they only did the synchronization of past conversations in order to disincentivize account sharing 😁. But with your model, where every token is billed, account sharing is not an issue.

Is anyone successfully running #openclaw with the maple-proxy by for a private AI assistant? I deployed the docker container on my openclaw VM but sadly every couple of prompts I get back "null" or a json-formatted reply. No idea why, as other times it works fine. But with how often I get null replies, it is unusable as an agent with multi-step tasks. Tried with kimi-2.5. If anyone is using a similar setup, I would be happy to hear!