Amp

Terminal agent · OpenAI Chat, OpenAI Responses, Anthropic Messages, Gemini

Full guide

Format	Where to set it up
OpenAI Chat, OpenAI Responses, Anthropic Messages, Gemini	Settings → Model Routing → Add → Custom URL (or workspace Model Routing for a team); from the terminal — amp config model-providers (list, test, set-priority, edit-router…)

Setup

Copy the configuration and replace sk-... with your key from the Ailoot Dashboard. Prefer storing the key in the environment variable AILOOT_API_KEY, if the application supports it.

Before starting, request GET /v1/models with your Ailoot key. Choose an exact model ID whose methods include POST /v1/chat/completions, POST /v1/responses, POST /v1/messages, POST /v1beta/models/{model}:generateContent, then use that ID in the configuration. For agents, also check tool support and the features required by your client version.

Model Routing → Add → Custom URL
  Format:   anthropic-messages
  Base URL: https://api.ailoot.ai
  API key:  sk-...
  Model mapping:
    anthropic/claude-fable-5 -> anthropic/claude-fable-5

Second connection for GPT:
  Format:   responses
  Base URL: https://api.ailoot.ai/v1
  API key:  sk-...
  Model mapping:
    openai/gpt-5.6-sol -> gpt-5.6-sol

Check: amp config model-providers check-access --provider-model anthropic/claude-fable-5

Example model: claude-fable-5. Choose any other model from the catalog — check that it supports the format you need.

Good to know

Test

For the OpenAI format, the URL is https://api.ailoot.ai/v1 (or the full path if the application asks for a full URL).
For the Anthropic format, the URL is https://api.ailoot.ai without /v1.
For the Gemini format, the URL is https://api.ailoot.ai — the API origin. The example above does not show the full setup for this format; consult the client’s documentation for the path to use in the relevant field. The API route prefix is /v1beta.
Ask a short question. If you get an error, check the code and Request ID, then consult Errors and limits.
404 immediately after setup almost always means the URL is wrong: an extra or missing /v1.
402 — insufficient balance for the reserve. Agents reserve more than chat: why.

Application documentation: https://ampcode.com/docs/markdown/customize/model-routing

Still have questions? Send your Request ID and a description — we'll help you troubleshoot.Contact support