Toggle thinking on abliteration.ai

Toggle the thinking step on abliteration.ai with the thinking parameter on Chat Completions and Anthropic Messages.

abliterated-model thinks before it answers. Set "thinking": false at the top level of the request body to skip the thinking step, or leave it off to keep the default.

Endpoints

Endpoint	thinking toggle
POST /v1/chat/completions	✓
POST /v1/messages	✓
POST /v1/responses	Not supported yet

Default is true (thinking on).

Chat Completions

curl -s https://api.abliteration.ai/v1/chat/completions \
  -H "Authorization: Bearer $ABLIT_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "abliterated-model",
    "thinking": false,
    "messages": [{ "role": "user", "content": "Capital of France?" }]
  }'

Anthropic Messages

curl -s https://api.abliteration.ai/v1/messages \
  -H "Authorization: Bearer $ABLIT_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "abliterated-model",
    "max_tokens": 256,
    "thinking": false,
    "messages": [{ "role": "user", "content": "Capital of France?" }]
  }'