Connect Windsurf to Anoman AI

Step 1: Open Windsurf model settings

In Windsurf, open Settings and go to the Cascade / model configuration where custom providers are managed. Windsurf lets you register an OpenAI-compatible provider with your own base URL and key.

Step 2: Add Anoman as an OpenAI-compatible provider

Set the base URL to Anoman's OpenAI-compatible endpoint and paste your Anoman API key. Anoman is a drop-in replacement for the OpenAI API, so no other configuration is needed.

Base URL:  https://api.anoman.io/v1
API Key:   anm-sk-your-key-here

Step 3: Pick a model

Enter any model name available on Anoman. Windsurf forwards the model name to the base URL and Anoman routes it to the correct provider across 400+ LLMs.

# Any Anoman model works, e.g.:
gpt-4o
gpt-4o-mini
claude-sonnet-4-6
claude-haiku-4-5

Alternative: environment variables

If you launch Windsurf from a shell that forwards OpenAI environment variables, you can export them instead of editing settings.

export OPENAI_BASE_URL=https://api.anoman.io/v1
export OPENAI_API_KEY=anm-sk-your-key-here

Verify the guardrails are active

Every Anoman response carries guardrail result headers. Inspect them in your dashboard traces to confirm the pipeline is running on Windsurf requests — prompt-injection detection, PII masking, and content moderation all apply automatically.

X-Anoman-Guardrail-Injection: pass score=0.03
X-Anoman-Guardrail-Pii: pass
X-Anoman-Guardrail-Content: pass
X-Anoman-Cache: none