UberLLM

Aider

Aider connects to any OpenAI-compatible endpoint through two environment variables and the openai/ model prefix.

Setup

macOS / Linux:

export OPENAI_API_BASE=https://api.uberllm.dev/v1
export OPENAI_API_KEY=ull_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

Windows:

setx OPENAI_API_BASE https://api.uberllm.dev/v1
setx OPENAI_API_KEY ull_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

(Restart your shell after setx.)

Run

Prefix the model with openai/ so Aider routes it through the OpenAI-compatible path:

aider --model openai/deepseek/deepseek-v3.1

Notes

  • Aider may print a model warning for models it doesn't recognize — this is expected for third-party models and does not stop it from working.

  • To persist settings, put the two variables in a .env file in your repo (or ~/.aider.conf.yml with openai-api-base / openai-api-key).

  • Use a strong coding model for edit-heavy work; append :nitro for the fastest provider or :floor for the cheapest (see Models & routing):

    aider --model openai/deepseek/deepseek-v3.1:floor