Estimate your monthly OpenAI, Anthropic, or Gemini bill. Type in your average token usage and request volume; we compute the cost across every model and let you compare side by side.
| Model | Provider | Cost / req | Monthly | vs cheapest |
|---|---|---|---|---|
| Gemini 1.5 Flash | $0.0003 | $26.25 | cheapest | |
| Gemini 2.0 Flash | $0.0003 | $35.00 | 1.3x | |
| GPT-4o-mini | OpenAI | $0.0005 | $52.50 | 2.0x |
| Claude 3.5 Haiku | Anthropic | $0.0032 | $320 | 12.2x |
| o3-mini | OpenAI | $0.0039 | $385 | 14.7x |
| Gemini 1.5 Pro | $0.0044 | $438 | 16.7x | |
| Mistral Large 2 | Mistral | $0.0060 | $600 | 22.9x |
| GPT-4o | OpenAI | $0.0088 | $875 | 33.3x |
| Claude 3.5 Sonnet | Anthropic | $0.012 | $1,200 | 45.7x |
| Claude Opus 4 | Anthropic | $0.060 | $6,000 | 228.6x |
Standard tier prices, 2026-06-16. No cache or batch discounts applied. Click a model name for the full breakdown.
Cost per request equals input tokens times the input price plus output tokens times the output price, divided by 1,000,000. Multiply by requests per month and you have a monthly estimate. The calculator hardcodes the latest published standard-tier prices (2026-06-16) for ten common models. For per-model breakdowns including cache discounts and batch tier pricing, see the dedicated pages under /pricing/<model>.
For real spend rather than estimates, instrument your app with Spanlens and capture every call with exact token counts and cost. The free tier covers 50K requests per month, more than enough to see whether your estimate matches reality.