RAG Chunk Simulator
Split documents into RAG chunks with overlap, variance heatmaps, and cost estimates.
OpenEstimate multi-model API cost from tokens or pasted prompts. - runs entirely in your browser. Free, fast and private.
Add input and output text, or type token numbers directly.
See GPT, Claude, Gemini, and more side by side.
Scale by calls per day to estimate your bill.
Get a recommendation within your token budget.
A feature that calls three models on every request can surprise the finance spreadsheet. LLM Cost Estimator estimates spend from token counts or pasted prompts across common model price points before you ship.
Plan budgets for chat features, batch summarization, and eval harnesses. Estimates follow public list prices you configure or select; your negotiated cloud discounts may differ. Tokenizers also differ by vendor, so treat results as directional.
Pitfall: counting only output tokens when the prompt and system message dominate cost. Include both directions.
Tip: paste a realistic prompt, not a one-line stub, when you are sizing a production path. Pair with Prompt Optimizer if you are trying to shrink instructions after you see the estimate.
Prompt text is measured in the page for estimation. We do not send your prompts to a model provider from this calculator.
Processes data instantly with no server round-trips.
Your data never leaves your browser. Nothing is uploaded.
Works in any modern browser. Nothing to download or install.
No limits, no sign-up, no credit card required.
Works on desktop, tablet and mobile devices.
Beautiful in both themes. Your preference is saved.
Keyboard shortcut
Ballpark monthly cost before enabling an LLM path.
Compare rough cost across candidate models for the same tokens.
Turn token math into a shareable estimate for planning.
Answers for this tool. For site-wide help, open the FAQ hub.
Many AI helpers on OneDevToolkit are local prompt builders, estimators, or rubrics. They do not call paid model APIs unless a tool explicitly says so.
Local tools do not upload prompts for training. If you later paste outputs into a third-party chat model, that vendor’s policy applies.
Token and cost estimators are approximations. Verify against your provider’s pricing calculator before budgeting.
Copy prompts into your notes, Vault, or Recipes. Clear the page when finished with sensitive instructions.
Be specific about role, constraints, and output format. Iterate with smaller samples before long documents.
Share final prompt templates via your internal wiki. Avoid putting API keys into browser tools.
Prompt craft tools work offline after load. Live model calls (if any) need network access.
You are responsible for how generated content is used. Follow your organisation’s AI policy.
Suggest improvements through Contact - include the tool URL and a redacted example.