// Cost IntelligenceLLM Cost
LLM Cost
Estimator
Know your spend before you ship. Every token has a price tag.
Calculate AI API costs across Claude, GPT, and Gemini. Compare providers side-by-side, optimize with caching and batching, and find the cheapest model that meets your quality floor.
// Model
// Workload
tokens
tokens
// Optimizations
Daily
$1.05
Monthly
$31.50
Annual
$383.25
// Cost per request — Sonnet 4.6
Input
$0.0030
Output
$0.0075
Total$0.010
// Optimization opportunities
Enable caching (50% hit rate) to save$4.05/mo
Use Batch API (50% discount, up to 24h latency) to save$15.75/mo
Route simple tasks to Haiku 4.5 to save$21.00/mo
// Break-even analysis
Sonnet 4.6→Haiku 4.5saves $21.00/mo
Best for classification, routing, and simple extraction
// Pricing reference (per 1M tokens)
| Provider | Model | Input | Output |
|---|---|---|---|
| Claude | Haiku 4.5 | $1 | $5 |
| Claude | Sonnet 4.6 | $3 | $15 |
| Claude | Opus 4.8 | $5 | $25 |
| Claude | Fable 5 | $10 | $50 |
| OpenAI | GPT-4o-mini | $0.15 | $0.6 |
| OpenAI | GPT-4o | $2.5 | $10 |
| OpenAI | o1 | $15 | $60 |
| Gemini | Flash | $0.075 | $0.3 |
| Gemini | Pro | $1.25 | $5 |