AI API cost calculator
How much will your app cost per month? Pick a workload or enter your own numbers and compare 443 models.
Prices from Oct 21, 2026
| # | Model | Per month |
|---|---|---|
| 1 | Ling 3.0 Flash | $9.22 |
| 2 | gpt-oss-20b | $12.10 |
| 3 | Nex-N2.5-Mini | $12.54 |
| 4 | Mistral Nemo | $12.96 |
| 5 | Gemma 3 4B | $14.28 |
| 6 | Extract | $14.40 |
| 7 | Summarize | $14.40 |
| 8 | Granite 4.0 Micro | $15.53 |
| 9 | Qwen3.7 Flash | $16.54 |
| 10 | GLM Flash Latest | $16.82 |
| 11 | GLM 5.3 Flash | $16.82 |
| 12 | gpt-oss-20b (batch) | $18.05 |
| 13 | Llama 3 8B Lunaris | $18.60 |
| 14 | Ministral 3 8B 2512 (batch) | $18.72 |
| 15 | Mercury 2.5 | $19.22 |
Costs = requests × 30 days × (uncached input × input price + cached input × cached price + output × output price). Long-context prices apply automatically above each model’s threshold. Taxes, minimums and rate limits are not included.