Every free AI model.
One endpoint.
ScoutCode pools the free tiers of the major AI providers behind a single OpenAI-compatible API. When one model runs out of quota, the next one answers.
One endpoint
OpenAI-compatible Chat Completions. Point Cline, Continue, Aider, Cursor or any OpenAI SDK at one base URL.
Automatic fallback
When a model hits a rate limit, errors or stalls, the next one takes over, even mid-stream before the first token.
Key rotation
Several keys per provider, used round-robin. Rate-limited keys cool down for exactly as long as the provider asks.
Presets
Clients ask for a friendly model name. Each preset maps to a ranked list of provider models.
Tools and vision
Tool calls and images are routed only to models that support them, and translated between providers.
Self-hosted
Your keys stay on your machine. Per-key rate limits, revocable client keys and a local dashboard.
Drop-in for the OpenAI API
Use model: "auto" and ScoutCode picks the best available model for you. Full API reference
curl https://your-scoutcode/v1/chat/completions \
-H "Authorization: Bearer sk-scout-…" \
-H "Content-Type: application/json" \
-d '{"model":"auto","messages":[{"role":"user","content":"Hello!"}]}'