Free · Open · Updated monthly
Calculate AI API costs in seconds.
Compare pricing across 23+ 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 2026-08-01·USD / CNY / EUR / GBP / INR
✓ Exact tokenizer·$5.00 in·$30.00 out (per 1M)
Quick start with a use case
Total cost per call$0.0200
Input$0.005000
Output$0.0150
Cost comparison
Standard
$0.0200
With Caching
$0.0177
Save 11% ↓
With Batch
$0.0100
Save 50% ↓
Cutting costs? Open models start at $0.14/1M
DeepSeek, Kimi & 200+ open models on Novita AI — often 5–20x cheaper than proprietary APIs for comparable tasks.
Affiliate link — we may earn a commission at no extra cost to you.
Side by side
All 23 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
| DeepSeek V4-Flash DeepSeek · small | $0.1400 | $0.2800 | $0.000280 | |
| DeepSeek V3.2 DeepSeek · balanced | $0.2800 | $0.4000 | $0.000480 | |
| GPT-5.6 Luna OpenAI · small | $0.2000 | $1.2000 | $0.000800 | |
| GPT-5 mini OpenAI · small | $0.2500 | $2.0000 | $0.001250 | |
| Mistral Large 3 Mistral · balanced | $0.5000 | $1.5000 | $0.001250 | |
| Gemini 3.5 Flash Lite Google · small | $0.3000 | $2.5000 | $0.001550 | |
| Gemini 3 Flash Google · balanced | $0.5000 | $3.0000 | $0.002000 | |
| o4-mini OpenAI · reasoning | $1.1000 | $4.4000 | $0.003300 | |
| Claude Haiku 4.5 Anthropic · small | $1.0000 | $5.0000 | $0.003500 | |
| Grok 4.5 xAI · flagship | $2.0000 | $6.0000 | $0.005000 | |
| Gemini 3.6 Flash Google · balanced | $1.5000 | $7.5000 | $0.005250 | |
| Gemini 3.5 Flash Google · balanced | $1.5000 | $9.0000 | $0.006000 | |
| Claude Sonnet 5 Anthropic · balanced | $2.0000 | $10.0000 | $0.007000 | |
| GPT-5.6 Terra OpenAI · balanced | $2.0000 | $12.0000 | $0.008000 | |
| Gemini 3.1 Pro Google · flagship | $2.0000 | $12.0000 | $0.008000 | |
| Grok 4 xAI · flagship | $3.0000 | $15.0000 | $0.0105 | |
| Claude Opus 5 Anthropic · flagship | $5.0000 | $25.0000 | $0.0175 | |
| Claude Opus 4.8 Anthropic · flagship | $5.0000 | $25.0000 | $0.0175 | |
| Claude Opus 4.7 Anthropic · flagship | $5.0000 | $25.0000 | $0.0175 | |
| GPT-5.6 OpenAI · flagship | $5.0000 | $30.0000 | $0.0200 | |
| GPT-5.6 Sol OpenAI · flagship | $5.0000 | $30.0000 | $0.0200 | |
| GPT-5.5 OpenAI · flagship | $5.0000 | $30.0000 | $0.0200 | |
| Claude Fable 5 Anthropic · flagship | $10.0000 | $50.0000 | $0.0350 |
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
3.6 FlashGooglecheapest
$90.0000/moper call: $0.003000year: $1095.00
Opus 5Anthropic
$300.00/moper call: $0.0100year: $3650.00
GPT-5.6OpenAI
$345.00/moper call: $0.0115year: $4197.50
Choosing 3.6 Flash over GPT-5.6 saves $255.00/month ($3060.00/year).
✓Last verified 2026-08-01✓Schema v2.0✓Updated monthly✓Open source on GitHub