Reasoning effort

Choose a model-compatible reasoning level for an assistant, conversation or individual message.

Reasoning effort controls how much reasoning a supported model uses. Set a saved default on an assistant, override it for a conversation, or choose a different level for one message. The selected model determines which levels are available.

Find compatible levels

Request the current catalog with your API key:

curl https://api.devic.ai/api/v1/models \
  -H "Authorization: Bearer $DEVIC_API_KEY"

devic models list
devic models list --provider open-ai --model gpt-6-luna

The response’s data array groups models by provider. Each model includes its identifier, reasoningEfforts, and reasoning/vision capabilities. A provider’s reasoningEfforts is the union of its selectable models’ levels. Use the model’s list to choose a value. An empty list means no named effort can be selected; omit the field or use null to keep the model’s default behavior.

The API recognizes none, minimal, low, medium, high, xhigh and max. Each model supports only a subset. Unsupported combinations return HTTP 400, including when changing the model while retaining an incompatible effort.

Assistant default

Include reasoningEffort when creating an assistant or updating it:

curl -X PATCH "https://api.devic.ai/api/v1/assistants/$ASSISTANT_ID" \
  -H "Authorization: Bearer $DEVIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"reasoningEffort":"high"}'

devic assistants update "$ASSISTANT_ID" --reasoning-effort high

The CLI’s assistants create command accepts the same flag, including alongside --from-json. Set null in API JSON, or --reasoning-effort default in the CLI, to remove the assistant’s explicit effort and use the adapter default.

Conversation and message overrides

Send these fields to the message endpoint:

{
  "message": "Review this proposal carefully",
  "chatUid": "existing-chat-id",
  "conversationReasoningEffort": "low",
  "reasoningEffort": "high"
}

This turn uses high; following turns use the saved conversation value low unless they include another message override. The message-level setting also applies to tool iterations and resumptions within that turn. Both synchronous and asynchronous requests accept these fields. Omit chatUid to start a new conversation with the same settings.

devic assistants chat "$ASSISTANT_ID" --chat-uid "$CHAT_UID" \
  -m "Review this proposal carefully" \
  --conversation-reasoning-effort low --reasoning-effort high

Field	Scope	If omitted	If null
Assistant reasoningEffort	Saved assistant default	Preserve it on PATCH	Use the adapter default
Message conversationReasoningEffort	Saved conversation default	Preserve the current conversation setting	Inherit the assistant setting
Message reasoningEffort	Current user turn	Inherit the conversation, then assistant	Inherit the conversation, then assistant

Resolution is message → conversation → assistant → adapter default. none is an explicit model level, distinct from inheritance. The CLI translates default (also accepted as null) into JSON null. API JSON must use null, not the string "default". Explicit CLI flags override JSON input, including when clearing a setting.

To restore assistant inheritance for an existing conversation:

devic assistants chat "$ASSISTANT_ID" --chat-uid "$CHAT_UID" \
  -m "Continue" --conversation-reasoning-effort default

Read the configured and effective values

Assistant reads include reasoningEffort. Conversation history includes reasoningEffort (the saved conversation setting) and effectiveReasoningEffort (the last recorded model call). Individual model response messages expose messageTokenUsage.reasoningEffort. An absent effective value indicates that the adapter’s existing default behavior was used.

devic assistants get "$ASSISTANT_ID"
devic assistants chats get "$ASSISTANT_ID" "$CHAT_UID"

In the console, the effort selector appears next to the model selector. Workspace assistant settings also provide it. Linked workspace assistants inherit the source setting unless a local override is saved; clearing that override restores inheritance. Workspace configuration uses its existing session-authenticated API and workspace permissions.