Token Cost Calculator
Compare LLM API pricing across providers and estimate costs
Usage Parameters
Presets:
Model Cost Comparison
A month is counted as 30 days
| Provider | Model | Input ($/1M) | Output ($/1M) | Per call | Per day | Per month | vs cheapest |
|---|---|---|---|---|---|---|---|
| Gemini 1.5 FlashCheapest | $0.075 | $0.30 | $0.00022 | $0.0225 | $0.6750 | 1.0x | |
| OpenAI | GPT-4o-mini | $0.15 | $0.60 | $0.00045 | $0.0450 | $1.35 | 2.0x |
| DeepSeek | DeepSeek-V3 | $0.27 | $1.10 | $0.00082 | $0.0820 | $2.46 | 3.6x |
| Anthropic | Claude 3.5 Haiku | $0.80 | $4.00 | $0.00280 | $0.2800 | $8.40 | 12.4x |
| Gemini 1.5 Pro | $1.25 | $5.00 | $0.00375 | $0.3750 | $11.25 | 16.7x | |
| Qwen | Qwen-Max | $1.60 | $6.40 | $0.00480 | $0.4800 | $14.40 | 21.3x |
| OpenAI | GPT-4o | $2.50 | $10.00 | $0.00750 | $0.7500 | $22.50 | 33.3x |
| Anthropic | Claude 3.5 Sonnet | $3.00 | $15.00 | $0.0105 | $1.05 | $31.50 | 46.7x |
At this usage, Gemini 1.5 Flash is the cheapest (about $0.6750/month); the most expensive, Claude 3.5 Sonnet, costs 46.7x more.
Prices are official list prices (USD / 1M tokens) for estimation only; actual billing depends on each provider's latest pricing, caching and tiered discounts.