Cost to Review 100 Pull Requests with LLM APIs

Each pull request review requires ~8,000 input tokens (the diff, surrounding code context, and review instructions) and ~1,000 output tokens (review comments, suggestions, and summary). Larger PRs will proportionally increase input tokens. Code review is input-heavy because the model must understand the full context of changes.

Formula: cost = (input_tokens × input_price_per_Mtok + output_tokens × output_price_per_Mtok) × quantity / 1,000,000

All prices are per million tokens, sourced directly from official provider pricing pages. No fabricated numbers — every model in the table links to its detail page, which cites the official pricing source.

How much does it cost to review 100 pull requests with an LLM?

It depends on the model. Code review is input-heavy (~8,000 input / ~1,000 output tokens per PR) because the model reads the diff and surrounding context. The calculator above computes the exact current cost for every model, cheapest-first, from live per-million-token pricing — see the table above for exact per-model cost at your PR volume.

Which LLM is best for automated code review?

For cost, the models at the top of the cost table above are cheapest. For review quality — catching subtle bugs and suggesting improvements — higher-tier models are typically stronger but cost more per PR. Compare exact figures in the calculator to choose.

How are code review token costs calculated?

Each PR review uses ~8,000 input tokens (diff + context) and ~1,000 output tokens (review comments). Total cost = (input_tokens × input_price + output_tokens × output_price) × number_of_PRs. Prices are per million tokens from official provider pricing.