Free · Open · Updated monthly

Calculate AI API costs in seconds.

Compare pricing across 10+ models from OpenAI, Anthropic, Google, DeepSeek, xAI and Mistral — including cached input and Batch API discounts.

  • Exact tokenization for OpenAI models, transparent estimates for others
  • Side-by-side caching & batch savings
  • Monthly cost forecasts for high-volume workloads
Updated 2026-05-05·USD / CNY / EUR / GBP / INR
✓ Exact tokenizer·$5.00 in·$20.00 out (per 1M)
Quick start with a use case
Total cost per call$0.0150
Input$0.005000
Output$0.0100
Cost comparison
Standard
$0.0150
With Caching
$0.0131
Save 12% ↓
With Batch
$0.007500
Save 50% ↓
Side by side

All 10 models, ranked by cost

Plug in your token usage. Sort, filter, hide. The cheapest pick for your workload is at the top.

All models compared

Sorted by cost for your token usage. Click column headers to re-sort.

Filter by provider
GPT-5 mini
OpenAI · small
$0.2000$0.8000$0.000600
DeepSeek V4
DeepSeek · balanced
$0.3000$1.2000$0.000900
Gemini 3.0 Flash
Google · balanced
$0.2500$2.0000$0.001250
o4-mini
OpenAI · reasoning
$0.9000$3.6000$0.002700
Claude Haiku 4.5
Anthropic · small
$1.0000$5.0000$0.003500
Mistral Large 3
Mistral · flagship
$2.5000$7.5000$0.006250
Gemini 3.0 Pro
Google · flagship
$1.5000$12.0000$0.007500
Grok 4
xAI · flagship
$4.0000$20.0000$0.0140
GPT-5.5
OpenAI · flagship
$5.0000$20.0000$0.0150
Claude Opus 4.7
Anthropic · flagship
$15.0000$75.0000$0.0525
Plan ahead

Forecast your monthly bill

Enter your daily call volume and average tokens. See the monthly damage across up to 5 models with savings highlighted.

Monthly cost forecast

Estimate your monthly bill across up to 5 models.

3/5 selected
Gemini 3.0 ProGooglecheapest
$130.50/mo
per call: $0.004350year: $1587.75
GPT-5.5OpenAI
$255.00/mo
per call: $0.008500year: $3102.50
Opus 4.7Anthropic
$900.00/mo
per call: $0.0300year: $10950.00
Choosing Gemini 3.0 Pro over Opus 4.7 saves $769.50/month ($9234.00/year).
Last verified 2026-05-05Schema v2.0Updated monthlyOpen source on GitHub