PricePerToken compares API costs for language models from multiple providers.
LLM Pricing
Calculate language model API costs using input, cached input, and output token counts.
About LLM Pricing
LLM Pricing is a web-based calculator for estimating the cost of language model API usage. You enter the number of input (prompt) tokens, cached input tokens, and output (completion) tokens, together with the cost per million tokens for each of those categories, and the tool returns a total cost. The page also lists model prices per million tokens, with options to show only selected models, clear a selection, sort by input or output cost, and compare models.
Key features
- Calculates total API cost from input, cached input, and output token counts
- Separate rate fields per million input, cached input, and output tokens
- Browse model prices listed per million tokens
- Show only selected models or clear the selection
- Compare models by input and output cost
- Displays a last-updated date for the price data
Best for: Developers and teams who want a quick estimate of LLM API costs from token volumes and per-million-token rates.
Good for
- Handles cached input tokens as a separate cost line rather than folding them into input cost
- Lists model prices in one place with selection and comparison controls
- States the tokenizer caveat that direct token-based price comparisons may not be entirely accurate
Watch out for
- Results depend on the token counts and per-million-token rates entered or selected
- Cross-model price comparisons based on tokens may not be entirely accurate because models use different tokenizers
- Price data carries a last-updated date, so figures may not reflect current provider pricing
LLM Pricing at a glance
- Website
- llm-prices.com
- Category
- AI & Machine Learning › AI Data & Analytics
- Type
- Website
- Pricing
- Not confirmed. Check the site
- Platforms
- Web
- Open source
- Not stated
- Language
- English
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
LLM Pricing alternatives
Tools and sites you could use instead, ranked by how closely they match.
ccusage analyzes token usage and estimated costs for coding agent command-line tools.
Indico benchmarks language models on extractive, classification, and predictive tasks.
SimpleBench evaluates everyday reasoning by comparing language models with human performance.
Deploybase compares GPU cloud and language model API prices, performance benchmarks, and provider market data.
OpenRouter publishes language model rankings based on real usage through its API.
Popular in AI Data & Analytics
Well-known listings from the same topic.
Dotgetdot.aiForvioforvio.comFluidAI Medicalfluidai.mdApache Zeppelinzeppelin.apache.orgSola Securitysola.securityQuadraticquadratichq.com
LLM Pricing FAQ
What token types does the calculator use?
It takes the number of input tokens (prompt tokens), cached input tokens, and output tokens (completion tokens), along with the corresponding cost per million tokens for each.
Can token-based prices be compared directly between models?
Not reliably. The page notes that different models use different tokenizers, so direct token-based price comparisons may not be entirely accurate.
Is the model price list kept current?
The page displays a "prices last updated" date, which indicates when the listed figures were last refreshed.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.