Hi everyone, is there any way to use models from the Qwen Cloud token plan on OpenHands? I tried setting this up in the advanced configuration using the OpenAI-compatible URL, but I don't know the correct format for the model ID, with or without the prefix, like in LiteLLM. Anyway, using only the model ID from the provider's documentation is not working. Thanks for any help! 😄

Hey! I'd try either: • the same prefix/modelname as litellm docs say • add openai/ in front of that, openai/prefix/modelname

Yeah, if you could share the values that you’re using now we could take a look!

For OpenAI this is the endpoint: token-plan.maas.qwencloudapi.com/compatible-mode/v1 the model id for example:

qwen3.8-max

Yes, we use litellm. Did you try

qwencloud/qwen3.8-max

as the model name?

Hi guys, with

openai/

prefix works very well 😄 thanks for the help