Run Use Wild West API in Continue
Continue's config.yaml takes an OpenAI-style provider with a custom apiBase. The VS Code and JetBrains extensions cannot read your shell environment, so the key goes in Continue's own .env.
- Base URL
- https://wildwestapi.com/v1
- API key
- Get one free, starts sk-ww-
- Example model
- outlaw-1-xploded
A models block in config.yaml
In ~/.continue/config.yaml:
YAML
name: Wild West API version: 0.0.1 schema: v1 models: - name: GLM 5.3 Flash Xploded (Wild West API) provider: openai model: outlaw-1-xploded apiBase: https://wildwestapi.com/v1 apiKey: ${{ secrets.WILDWEST_API_KEY }} capabilities: - tool_use roles: - chat - edit - apply
Put WILDWEST_API_KEY=sk-ww-... in ~/.continue/.env. The capabilities: [tool_use] line matters: Continue drops Agent mode for a model id it does not recognise unless you declare tool use, so set it only for a tool-capable model.
Pick a model
Each page has the Continue setup with that model's id and limits filled in, and what a session costs.
Outlaw 1 Xploded in Continue1M context, $0.30 in / $1.00 out per 1M
GLM 5.3 Xploded in Continue1M context, $2.50 in / $4.50 out per 1M
GLM 5.3 Flash Xploded in Continue1M context, $0.40 in / $1.60 out per 1M
MiMo V2.6 Flash Xploded in Continue1M context, $1.00 in / $3.00 out per 1M
Qwen3.8 27B Xploded in Continue524K context, $0.30 in / $2.40 out per 1M