Use aider with any model via one gateway

aider talks to any OpenAI-compatible endpoint through two environment variables — no config file needed.

Setup

  1. Create an account and copy your wk_live_… key (shown once).
  2. Export the base URL and key, then start aider:
bash 
export OPENAI_API_BASE=https://gateway.webik.ai/v1
export OPENAI_API_KEY=wk_live_...
aider --model openai/auto/code

The openai/ prefix tells aider to use its OpenAI-compatible client — the request goes to WebikAI, not to OpenAI. Everything after the prefix is the WebikAI alias or model slug.

Models to start with

auto/codeCoding route ranked under your policy
auto/cheapAggressively minimize cost
auto/frontierPremium frontier route under your policy
z-ai/glm-5.2Pin an exact model (OpenRouter-style slug)

Receipts and budgets

Every response carries five x-webik-* headers naming the request id, the model and provider that actually served it, the credential used (byok/managed), and whether a fallback fired. Requests stop at your per-key and per-client budget caps — before forwarding, never after.

Full reference: docs · live scores: benchmarks · start free