Skip to content

Configure Reasoning Effort

Use the reasoning control in the composer to adjust how much thinking budget a model spends on its next reply. Available levels depend on the active model and are saved per chat.

Adjust reasoning effort to allow a shorter or longer planning process before an answer.

Using the Reasoning Effort Slider in the Web UI

  1. Open a chat and open the model picker in the composer.
  2. Select a model that supports configurable reasoning.
  3. Move the Reasoning effort slider (or use the left/right arrow keys when focused) to pick a level.
  4. Send your message.

The control adapts to the selected model's catalog entry:

  • effort mode: Offers the model's supported effort steps (such as low, medium, high, xhigh, max), plus Off when reasoning is optional (reasoning_mandatory: false).
  • enabled mode: Offers an On / Off toggle when reasoning is optional, or stays enabled when mandatory.
  • native and none modes: Use fixed provider behavior without an effort slider.

Lower effort levels reduce time-to-first-token for quick questions; higher levels give the model more room to plan complex code changes, math, or multi-step tool use.

Mandatory vs Optional Reasoning

Whether reasoning can be turned Off is controlled by reasoning_mandatory in the model catalog. When you switch a chat to a different model, Numi automatically normalizes the chat's saved reasoning setting to the closest level supported by the new model.

Administrators can view or edit reasoning_efforts, reasoning_default_effort, and reasoning_default_enabled on the admin Models page (and use Refresh provider metadata for OpenRouter models). See Manage Models.

Programmatic Configuration via API

Set Reasoning Level

Update the reasoning level for a chat you own:

curl -X POST http://localhost:4567/api/v1/chats/YOUR_CHAT_UUID/reasoning \
  -H "Authorization: Bearer YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"reasoning_level": "high"}'

Response:

{
  "status": "success",
  "message": "high"
}

message returns the normalized level that was saved (for example, requesting "off" on a mandatory-reasoning model resolves to its default enabled effort).

Supported Effort Values

The chat endpoint accepts:

off, minimal, low, medium, high, xhigh, max

Always pass "off" (not "none") to disable optional reasoning via the Numi API; the wire adapter translates "off" to the upstream provider's format (such as reasoning: {"effort": "none", "exclude": true} on OpenRouter) automatically.

Reasoning Modes

Catalog reasoning_mode UI & Adapter Behavior
effort Exposes the model's reasoning_efforts list (plus off when reasoning_mandatory is false)
enabled Exposes an on/off toggle when optional, or keeps reasoning enabled when mandatory
native Model reasons natively without an effort parameter (for example, Z.AI or local <think> models)
none Non-reasoning model

Preserved Reasoning Across Turns

Reasoning effort controls how much the model thinks on the current turn, while preserve_reasoning controls whether returned reasoning traces are replayed in history on subsequent turns. See Preserved Reasoning and Model Catalog Reference for details.