uncensoredlabs
Log inGet started
Docs
API referenceSign in

Get started

The core loop

The workflow is simple: sign in, check credit, select a model, send a request, and review its usage.

Prepare your account

  1. Create an application key with an appropriate spending limit.
  2. Check available credit, including any credit currently reserved.
  3. Select an enabled model and confirm the capabilities your application needs.

Call a model

POST /v1/chat/completions 
curl "https://uncensoredlabs.dev/v1/chat/completions" \
  -H "Authorization: Bearer $UNCENSOREDLABS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"YOUR_APPROVED_MODEL_ID","messages":[{"role":"user","content":"Hello"}],"max_tokens":256}'

Set a conservative output limit. Requests that exceed a model's context or output limits are rejected before inference.

Read usage

Open Usage / Activity to inspect the model, API key, token counts, status, duration, and charge. Spend shows totals and breakdowns within the configured activity-retention window.

Use the response's x-request-id when investigating a call. Missing or invalid provider usage can leave credit reserved while the result is reconciled.