Usage & Billing

The API is pay per token: you top up credits, and every request deducts the tokens it consumed. There are no subscriptions and no minimum commitment.

Credits

Your account has a credit balance, managed in the Credits & Billing page of the UncensoredGPT Console:

Top up any amount (minimum 5 USD per top-up).
Credits are shared by all the keys on your account.
When your balance reaches zero, requests are rejected until you top up again. Your keys and settings are untouched.

Each model has its own per-token price, shown in the Console’s Models page. Input and output tokens are priced separately — output tokens usually cost more.

Track your usage

The Usage page in the Console shows:

Totals — cost, tokens, and requests over any time range.
Charts — daily cost, token usage, and request volume.
Usage logs — every request with its model, tokens, cost, throughput, and latency, filterable by model and status, exportable to CSV.

Usage statistics update in near real time, but the numbers you see are for information only. Your credit balance is always the authoritative amount.

Estimate costs before you send

Cost is simply tokens × price. As a rough rule for open-source models, 1,000 tokens ≈ 750 English words. The token count of each request is returned in the usage field of every response:

{
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 98,
    "total_tokens": 110
  }
}

Billing history

Invoices and payment receipts are available in Credits & Billing. For anything else, contact info@uncensoredgpt.ai.

Introduction

Coding agents

Chat

Completions

Embeddings

Responses

Models

Moderations

Batches

Files

Images

Messages

Credits

Track your usage

Estimate costs before you send

Billing history