Transparency Hub

How Credits Work

No hidden multipliers, no obscure logic. Here is exactly how your credits are calculated.

The Formula

Credits Used = (Input Tokens ÷ 1,000 × Input Rate) + (Output Tokens ÷ 1,000 × Output Rate)

Input and output tokens are priced separately because generating output costs significantly more than reading input. Each model has its own input and output rate based on the real API cost from the provider. The result is kept to two decimal places for precise billing.

Why Separate Rates?

AI providers charge very differently for input vs. output tokens. For example, GPT-5.4 output costs 6× more than input at the API level. By splitting the rates, we can price each model fairly and transparently.

Short prompts with long responses cost more than the reverse.
Lightweight models stay cheap even for long conversations.
You always pay proportionally to the real cost of the model.

Credit Rates per Model

Model	Provider	Input Ratecredits per 1K tokens	Output Ratecredits per 1K tokens	Description
GPT-5.4 BASE	OpenAI	0.50	3.00	Latest and most advanced GPT model
GPT-5.4 Pro	OpenAI	6.00	36.00	High-intelligence professional model
GPT-5.2	OpenAI	0.35	2.80	Previous generation base model
GPT-5.2 Pro	OpenAI	4.20	33.60	Previous gen professional model
GPT-5.2 Codex	OpenAI	0.35	2.80	Optimized for code generation
GPT-5.1	OpenAI	0.25	2.00	Previous generation base model
GPT-5 mini	OpenAI	0.05	0.40	Lightweight efficient model
GPT-5 nano	OpenAI	0.01	0.08	Fastest, smallest model
Gemini 3.1 Pro	Google	0.50	3.20	Advanced reasoning for complex problem-solving
Gemini 3 Flash	Google	0.10	0.60	Fastest Gemini 3 model
Gemini 2.5 Pro	Google	0.25	2.00	Previous pro generation
Gemini 2.5 Flash	Google	0.06	0.50	High volume, low latency
Gemini 2.5 Flash Lite	Google	0.02	0.08	Cost effective lite model
Claude Sonnet 4.5	Anthropic	0.60	3.00	Balanced intelligence model
Claude Sonnet 4.6	Anthropic	0.60	3.00	Latest Sonnet with Opus-level intelligence
Claude Opus 4.5	Anthropic	1.00	5.00	Flagship reasoning model
Claude Opus 4.6	Anthropic	1.00	5.00	Latest Opus with deep reasoning

Rates are derived from each provider's published API pricing and are subject to change. We aim to update this table 30 days prior to any major changes.

Real-world Examples

Quick Chat

GPT-5 mini

Input (500 tokens)0.03

Output (300 tokens)0.12

Total1 credits

Rounded up from 0.15

Document Analysis

GPT-5.4

Input (5K tokens)2.50

Output (1K tokens)3.00

Total6 credits

Rounded up from 5.50

Complex Code Review

Claude Opus 4.6

Input (3K tokens)3.00

Output (2K tokens)10.00

Total13 credits

Ready to get started?

Pick a plan that works for you and start using credits across all models today.

View Plans