Skip to content
Convertto

Prompt Template Filler & Batch Expander

Write a prompt once with placeholders, paste rows of data, and get every filled prompt back with its token count and cost.

This tool fills a prompt template from CSV or JSONL data, expanding one template plus N rows into N ready-to-send prompts. It supports Handlebars, Python-format, JavaScript-literal and shell placeholder syntax, refuses to silently blank a missing variable, and reports the token count and estimated cost of the whole batch before you send any of it.

Runs in your browser
Privacy
Runs entirely in your browser — nothing is uploaded
Cost
Free, unlimited, no sign-up

Frequently asked questions

Why does it refuse to fill a missing variable?

Because a blank placeholder produces a prompt that still reads as valid English, gets a confident answer, and costs the same as a correct call. Failing loudly at template time is cheaper than discovering it in the output.

Can I use this to build a fine-tuning file?

Yes — choose the JSONL output and each row becomes a request body with a single user message. Add the assistant side with the dataset converter.

How to use the prompt template generator

  1. 1Enter or paste your template.
  2. 2Enter or paste your data.
  3. 3Choose the placeholder syntax.
  4. 4Choose the output as.
  5. 5Turn "Fail on missing variables" on or off as needed.
  6. 6Press Run, then download the result when it is ready.

Embed this tool

Put the working prompt template generator on your own site. It runs in your visitors' browsers exactly as it does here — free, no account, nothing uploaded.

Share this tool

Related tools

Context Window CalculatorPaste a document and see which models it fits inside, how much of each window it fills, and what is left for the reply.Prompt Token OptimizerStrip the padding out of a prompt — dead whitespace, boilerplate politeness, redundant framing — and see the tokens and money saved.AI API Cost CalculatorWork out what a prompt costs per call, per day and per month, and compare the same workload across every major model.LLM Model ComparisonEvery current model side by side: price per million tokens, context window, max output, modalities and cache rates.LLM Stream ParserPaste a raw server-sent-event stream and get the reconstructed message, tool calls, usage and stop reason.LLM Token CounterCount tokens with the real BPE vocabulary, see every token coloured in place, and compare the count across models.

Last updated

More ai & llm tools