You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I currently use Litellm proxy with aider. Aider has a built-in litellm_proxy argument that allows it to use any of your models defined in litellm. Like so aider --model litellm_proxy/gpt-4 --dark-mode --cache-prompts --no-attribute-committer or aider --model litellm_proxy/openrouter/gemini-2.5-pro --dark-mode --cache-prompts --no-attribute-committer --thinking-tokens=5k.
The same doesn't work with bifrost. I've tried setting the base api url to bifrost's openai compatible endpoint, to the litellm compatible endpoint, and using the same litellm_proxy argument to potentially trick aider, but nothing works. No combination of model names, provider prefixes, endpoint changes, etc., seems to work. Despite aider being extremely compatible with just about every AI provider and standard endpoints.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
I currently use Litellm proxy with aider. Aider has a built-in
litellm_proxyargument that allows it to use any of your models defined in litellm. Like soaider --model litellm_proxy/gpt-4 --dark-mode --cache-prompts --no-attribute-committeroraider --model litellm_proxy/openrouter/gemini-2.5-pro --dark-mode --cache-prompts --no-attribute-committer --thinking-tokens=5k.The same doesn't work with bifrost. I've tried setting the base api url to bifrost's openai compatible endpoint, to the litellm compatible endpoint, and using the same
litellm_proxyargument to potentially trick aider, but nothing works. No combination of model names, provider prefixes, endpoint changes, etc., seems to work. Despite aider being extremely compatible with just about every AI provider and standard endpoints.All reactions