Your Usage
▼
Monthly volume
API calls30,000
Input tokens15,000,000
Output tokens6,000,000
Estimated Cost
Monthly cost
$97.50
$3.25 / day · $1.2k / year
Cost breakdown
Input (2.5/1M tokens)$37.50
Output ($10/1M tokens)$60.00
TokenTune Optimization
With prompt caching, model routing, and batch optimization, typical savings are 30–50%.
Save $29.25 – $48.75/mo
estimated with TokenTune optimizations applied
Free Resource
Want a structured checklist for auditing your own LLM costs?
Model Pricing Referenceprices per 1M tokens, approximate as of 2025
| Model | Provider | Input / 1M | Output / 1M | Ratio |
|---|---|---|---|---|
| GPT-4o | OpenAI | $2.500 | $10.00 | 1:4.0x |
| GPT-4o-mini | OpenAI | $0.150 | $0.60 | 1:4.0x |
| Claude 3.5 Sonnet | Anthropic | $3.000 | $15.00 | 1:5.0x |
| Claude 3 Haiku | Anthropic | $0.250 | $1.25 | 1:5.0x |
| Gemini 1.5 Pro | $1.250 | $5.00 | 1:4.0x | |
| Gemini 1.5 Flash | $0.075 | $0.30 | 1:4.0x |
Prices are approximate and subject to change. Check each provider’s pricing page for current rates. Selected model highlighted in amber.