Home / Cost calculator
LLM cost per token calculator
Estimate request and monthly API spend across providers. Tune cache hit %, Batch API, and users × messages per day. Same TokenCalculator engine as the token calculator, cost first.
Full calculator · Tokenizer · Pricing guide · Prompt cost · Prompt caching · Pricing changelog
Cost and monthly spend
Set output length, cache hit rate, Batch API, and volume to project daily, monthly, and yearly API spend.
- Input tokens
- 77
- Output tokens
- 512
- Input cost
- $0.000154
- Output cost
- $0.004096
- Characters
- 306
- Words
- 51
Monthly projector
- Daily
- $2.125
- Monthly
- $63.75
- Yearly
- $775.62
Rates in $2.00/1M · out $8.00/1M
Context 589 / 1,000,000 · Verified · official pricing
loading o200k_base; temporary heuristic
Compare models
Same prompt, output size, cache, and batch settings across models.
| Model | Accuracy | Input tok | Request | Monthly |
|---|---|---|---|---|
DeepSeek V4 FlashDeepSeek | Approx | 77 | $0.000637 | $9.56 |
Gemini 2.5 FlashGoogle | Approx | 77 | $0.001303 | $19.55 |
GPT-4.1OpenAI | Approx | 77 | $0.00425 | $63.75 |
Claude Sonnet 5Anthropic | Approx | 77 | $0.005274 | $79.11 |
Related tools
Cheapest LLM API · Compare model prices · Cache savings · Batch pricing
Related guides
How LLM API pricing works · How prompt cost is calculated · Prompt caching explained · Exact vs Approx
Sources and references
Official documentation used for definitions, counting methods, or rate cards. Always confirm critical budgets on the provider page.
Cost calculator FAQ
- Is this a separate product from the token calculator?
- Same engine, cost first. This view keeps the spend projector and drops the per token visualiser. Tokenizer flips that around, and Home shows both.
- How do I estimate monthly spend?
- Set output tokens, optional cache hit % and Batch, then enter users and messages per day. The panel projects daily, monthly, and yearly cost.
- Are prices live?
- Rates are curated from official provider pages and stamped with a last-verified date on each model. Always confirm critical budgets on the provider’s pricing page.