LLM API cost calculator

Work out what a single call costs. Paste your prompt to auto-count input tokens with a real tokenizer, set how many output tokens you expect, pick a model, and see the cost split into input vs output. Output is usually the expensive half.

Input cost
—
Output cost
—
Total / call
—
Cost / 1,000 calls
—

Rates as of June 2026 (checked 2026-06-06) — standard list prices, excluding cached-input and batch discounts; verify on the provider's pricing page. Input-token counts are exact for OpenAI and estimates for other providers.

Why split input and output?

Providers charge different rates for the tokens you send (input) and the tokens the model writes (output) — output is typically 3–5× more expensive. A long prompt with a short answer behaves completely differently from a short prompt that generates a long answer, so estimating them separately is the only way to get a real number. Compare the same call across every model with the model cost comparison.

More free token tools

TokensToken counterPaste text, pick a model, and see exact tokens, characters, and chars/token — every token as a colored chip with its ID.CostModel cost comparisonOne prompt + expected output length, costed side by side across every model in a sortable table.TokensTokenizer visualizerSee exactly how text splits into tokens, color-coded, with hover to inspect each token's ID and boundaries.TokensContext window checkerPaste a prompt, pick a model, and find out whether it fits the context window — and how many tokens are left.TokensWord ↔ token estimatorQuick two-way converter between word count and token count, with real-tokenizer calibration.ExplainerFrom prompt to outputA clickable pipeline explaining how an LLM turns your prompt into output — tokenization, embeddings, transformer, sampling, and back.