Workload calculator
LLM API Cost Calculator
Estimate monthly API spend from tokens, requests, cache reuse, and batch pricing. Enter your workload first, or use a preset as a shortcut.
Usage input
Estimate a repeated workload from tokens per request, request volume, cache reuse, and optional batch pricing.
Choose a preset or scroll for custom input.
Explore benchmark scores to see which models perform best on specific tasks.
Input
Estimate input tokens from text
Text is processed only in your browser and is not saved or sent anywhere. This is a reference count for o200k_base, not the exact billable token count for the selected model or provider. It also excludes API message, tool, schema, image, and other request overhead.
Advanced options
Cost estimates use the generated model database last built on Sep 19, 2026. Pricing, lifecycle, and capability fields can be incomplete or provider-specific, so verify production decisions with the official provider.
How to use this page
Start with a preset for a forecast, then change tokens and request volume to match your product. If you already have token totals from a completed request or session, choose Use actual token usage and enter that breakdown directly.
How pricing is calculated
Costs are calculated as (tokens ÷ 1,000,000) × price per 1M tokens. Input and output tokens are priced separately — output is typically 3–5× more expensive. The cache hit rate reduces the effective input cost by applying a lower cached price to matched requests. The formula: total = (inputTokens × inputPrice + outputTokens × outputPrice) × requests × (1 − cacheDiscount).
Read the calculator examples guide for chatbot, RAG, summarization, and coding-agent inputs before changing the fields.
Check when a subscription is enough and when usage-based API pricing matters for product work.
Compare OpenAI, Anthropic, Google, Mistral, and DeepSeek across cheapest chat, mid-range, and reasoning model pricing.
See MMLU, GPQA, HumanEval, and other benchmark scores across providers to understand model quality beyond pricing.
Put 2-3 models next to each other to compare pricing, context windows, modalities, and capabilities.