Token Cost Calculator
Compare API pricing across all major AI models. See exactly what your prompts cost.
Advertisement
Output ratio: how many output tokens per input token (typical: 1-3x).
Cheapest Model
Gemini Flash
Your Daily Cost
$0.02
Your Monthly Cost
$0.60
Calls per $1
5,000
| Model | Provider | Input / 1M tokens | Output / 1M tokens | Your Input Cost | Your Total Cost |
|---|
Advertisement
How Token Pricing Works
AI providers charge based on token usage, split into two categories:
- Input tokens — what you send to the model (your prompt, system instructions, conversation history)
- Output tokens — what the model generates in response (typically 2-3x fewer than input, but at higher per-token rates)
Most providers also offer cached input pricing (discounted rates for repeated prompts) and long-context surcharges when your prompt exceeds certain thresholds.