# LLM token cost calculator: run it free, or from your agent

Cost per call and per month for any model in the OpenRouter list, from your own token counts.

## Prompt

Use looot to price this LLM workload: [model], [input tokens] input and [output tokens] output tokens per call, [calls per day] calls a day. 1. Set up https://looot.ai/skill.md. 2. Run the OpenRouter model list endpoint to read the current price per million tokens. 3. Work out the cost per call and per month for that model and the three cheapest models with at least the same context length. 4. Return one table and the date of the prices.

## What it needs

A model and the input and output tokens of one call

## What comes back

- cost of one call
- cost per day
- cost per month
- input and output price per million tokens
- the date the prices were read

## Endpoints and providers

None. The tool on the web page runs in the browser and calls no endpoint.

## What it costs

Nothing. The tool on the web page runs in the visitor's browser: no account, no API call and no limit per hour. The prompt above runs the same job from your own looot account with current data, billed per call.

## Budget a feature

Know what a chat feature costs per user before you build it.

## Pick a model

Compare the same workload across models and see where the money goes.

## Trim a prompt

See how much a shorter system prompt saves at your real call volume.

## Agent loops

Price an agent that makes many calls per task, not just one.

## How do I calculate the cost of an LLM call?

Multiply the input tokens by the input price per million tokens, add the output tokens times the output price, and divide by one million. The calculator does that for the model you pick.

## Where do the prices come from?

From the OpenRouter model list, read through looot on the date shown under the calculator. Prices change, so check that date before you quote a number.

## Is this calculator free?

Yes. It runs in your browser, needs no account and makes no API call. There is no limit on how often you use it.

## Why do output tokens cost more than input tokens?

Most providers price output higher because the model generates it one token at a time. The calculator shows both prices so you can see which side drives your bill.

## How many tokens is a word?

It depends on the model's tokenizer and the language. Count real prompts with the model's own tokenizer when the number matters, then type that count here.

## Does it include cached input or batch prices?

Batch variants appear as their own rows when the model list has them. Cached input and per-search fees are not in this list, so the calculator leaves them out.

## How does my agent get current prices?

Copy the prompt above. Your agent runs the OpenRouter model list endpoint through looot and works out the same numbers with today's prices.

## Can I compare several models?

Switch the model and the numbers update at once. For a table of many models, the model price page on looot lists every row of the same snapshot.

## Related tools

- /free-tools/youtube-transcript
- /free-tools/backlink-checker
- /free-tools/google-maps-scraper

## Last reviewed

2026-10-14.