Why separate input and output tokens per dollar?

Providers price input and output differently — output is usually three to five times more expensive. A model that is cheap for input can be expensive for output, so the most efficient model depends on whether your workload reads more than it writes.

What does input-heavy versus output-heavy mean?

Input-heavy workloads send large prompts and get short answers — summarisation, classification, retrieval. Output-heavy workloads send short prompts and generate long answers — content generation, code. Balanced is roughly equal. The leaderboard weights the blended price accordingly.

Does cheapest tokens per dollar mean best model?

No. Value is tokens per dollar at the quality you need. A budget model with huge tokens-per-dollar is useless if it fails your task. Use the quality filter to compare only models that clear your bar, then pick the most efficient one.

Are the prices current?

They are editable presets from published list prices and labelled as estimates. Providers change pricing often, so confirm the current rate before budgeting.

Is anything sent to a server?

No. The ranking is computed in your browser from a built-in price table. Nothing is uploaded.

Tokens-per-Dollar Leaderboard

Get the most tokens for every dollar

Two models can differ tenfold in how many tokens a dollar buys. This leaderboard ranks major LLMs by tokens per dollar, weighted for how you actually use them — input-heavy, output-heavy, or balanced — so the best-value model for your workload is the one at the top.

How tokens-per-dollar is computed

For a given workload mix we blend the input and output prices, then invert to get tokens per dollar:

blended_price = w_in x input_price + w_out x output_price   (per 1M tokens)
tokens_per_dollar = 1,000,000 / blended_price

For input-heavy work the input weight dominates; for output-heavy work the more expensive output price dominates, which is why output-heavy leaderboards look very different from input-heavy ones.

Tips for using the ranking

Match the workload weighting to reality. Ranking a content-generation app on input-heavy weights will recommend the wrong model.
Filter by quality first. Set the tier so you only compare models that can do the job, then maximise tokens per dollar within that set.
Re-check prices regularly. Provider price cuts reshuffle the leaderboard; a model that was mid-pack last quarter may now top it.