integrations/framework/LiteLLM

LiteLLM + AIgateway

Use LiteLLM as a proxy upstream of AIgateway.

Many enterprises already route through LiteLLM. Configure AIgateway as an OpenAI-compatible provider in LiteLLM's config and you keep your existing routing logic while gaining 1000+ models behind one upstream.

LiteLLM homepage →

Setup

Three steps or fewer.

STEP 01

Add to litellm config

Point a model entry at AIgateway with your key.

model_list:
  - model_name: kimi-k2.6
    litellm_params:
      model: openai/moonshot/kimi-k2.6
      api_base: https://api.aigateway.sh/v1
      api_key: os.environ/AIGATEWAY_API_KEY

More integrations

Same key. Every other tool.

OpenAI SDK

Drop-in. Change one line, gain 1000+ models.

Claude Code

Point Anthropic's CLI at AIgateway and pick any model in 30 seconds.

Cursor

Add AIgateway as a custom OpenAI-compatible provider in Cursor.

Cline

VS Code agent that runs on whichever model wins your eval.

Aider

Terminal-native pair programmer — works with one --openai-api-base flag.

Continue.dev

Open-source IDE assistant — drop AIgateway into config.json.