Heiryn Docs

Auto Model

Auto is the default chat model mode when no personal or server model has been selected.

In Auto mode, Heiryn starts with the configured standard model: DeepSeek V4.1 Flash 1017 (xs:deepseek). It switches to the configured pro model, DeepSeek V4.1 Flash 1017 (s:deepseek), only when one of these conditions applies:

  • at least one tool explicitly marked as dangerous is loaded for the request;
  • the model claimed to generate an image without calling the image tool, and Heiryn retries with that tool required; or
  • the requester uses Retry after an interrupted query.

On OpenRouter, both models are DeepSeek V4.1 Flash 1017 routed through different providers. The standard xs:deepseek route only uses providers priced within the Extra Small ceiling, which usually serve the model with lower-precision quantization. The pro s:deepseek route only uses providers serving it at 16-bit precision or without a reported quantization, which is typical of first-party APIs. When no provider within the Extra Small price ceiling is available, the standard route temporarily falls back to GLM 5.3 Flash for that request.

Long conversation history does not trigger the Pro model. History is compacted when it approaches its context budget instead.

This dynamic switch only happens while the resolved model is still Auto. If you select a model explicitly, Heiryn keeps that model for the request instead of upgrading it automatically, including for dangerous tools and retries after interrupted queries.

For example, selecting DeepSeek V4.1 Flash 1017 (xs:deepseek) explicitly is different from leaving the setting on Auto:

  • Auto: starts on DeepSeek V4.1 Flash 1017 (xs:deepseek) and may switch to DeepSeek V4.1 Flash 1017 (s:deepseek).
  • DeepSeek V4.1 Flash 1017 (xs:deepseek): stays on DeepSeek V4.1 Flash 1017 (xs:deepseek).

Resolution Order #

The chat model for a request is resolved in this order:

  1. A one-message model suffix.
  2. Your personal model preference.
  3. The server default model.
  4. Auto mode.

Server admins can set the server default model from the dashboard or with /community_chat_model. Users can set their personal preference from the dashboard or with /personal_chat_model.

When To Use Auto #

Auto is usually best when you want the bot to balance cost and quality without manual intervention. It keeps normal requests on the standard model and uses the Pro model only for the conditions listed above. Requester or staff status alone, long history, and ordinary safe tools do not trigger an upgrade.

Choose an explicit alias when you want a predictable cost category or the behavior of its current mapping. Explicit choices disable the automatic pro-model upgrade for that scope, but an alias may map to a newer qualifying model on a later request under the model alias policy.