1. Measure token input
Count prompt tokens and estimate the input charge for a representative request.
Count tokensEstimate monthly spend for model APIs, coding assistants, and common agent workloads using checked prices, token volume, requests, caching, team size, and plan limits.
Start with a verified price, a workload estimate, or a comparison that matches the decision in front of you. Browse coding tools.
Check input, cached input, and output prices per 1M and 1K tokens.
Check OpenAI API pricing API pricingCheck input, cache write, cache hit, and output prices per 1M and 1K tokens.
Check Claude API pricing Interactive comparisonChange token volume and requests to compare monthly API cost.
Open model comparison Coding-tool pricingCheck plans, team base fees, developer seats, and cost examples.
Check Windsurf pricing Token toolCount tokens before estimating model input cost.
Open token counter Cost methodologyWork from requests, token volume, output length, and caching.
Read the cost guideMeasure the work, price the usage, and compare the options that can change the total before you commit.
Count prompt tokens and estimate the input charge for a representative request.
Count tokensAdd output tokens, request volume, and caching to estimate a fuller API budget.
Calculate monthly costCompare models, providers, and coding-tool subscriptions before choosing a stack.
Compare costsSee the most-used entries below, or browse every tracked model.