# BerriAI/litellm SLOC report

> BerriAI/litellm: 2,074,295 code lines at commit 76e45df333c0, counted with tokei-15.0.0 on 2026-11-16. Saved result 5d5c3dc7ee671da1b89c11a3e01859883baa1f51b899ec8fdd2f113210571c41.

BerriAI/litellm has 2,074,295 source lines of code out of 2,447,295 total lines across 8,870 files, counted with tokei from the main ref at commit 76e45df333c0 on November 16, 2026. Tests, docs and generated files are excluded under OctoCounts' canonical public options.

OctoCounts produced this report by resolving BerriAI/litellm to commit 76e45df333c0, downloading the repository source archive, and counting files selected by the effective rules with tokei, the open-source line counter written in Rust. The table below breaks the count down by programming language into files, total lines, code lines, comment lines, and blank lines, so the figures can be compared across languages and projects. Results are cached by commit, tokei version, and analysis options; an exact reproduction needs the same commit, engine version, and effective counting rules.

## Counting rules and retention

BerriAI/litellm: tokei-15.0.0, policy directories-v1; docs excluded, tests excluded, generated excluded. Excluded directory names: .cache, .generated, .git, .next, __tests__, build, dist, doc, docs, documentation, fixtures, gen, generated, node_modules, target, test, tests, vendor. Ignored languages: none. Repository declarations: off. Exclusions are rule-based; they do not prove that every test, document or generated file was removed.

Saved reports remain subject to cache cleanup and replacement. Export the JSON or text for durable citation; live repository URLs can change.

## Repository size insights

This is a very large codebase by counted code lines. Code represents 84.8% of all lines, comments represent 5.8%, and the repository averages 234 code lines per file. Python accounts for 46.4% of counted code.

| Language | Files | Lines | Code | Comments | Blanks |
| --- | ---: | ---: | ---: | ---: | ---: |
| Python | 3,476 | 1,147,169 | 962,223 | 33,930 | 151,016 |
| JSON | 95 | 378,050 | 378,042 | 0 | 8 |
| TSX | 1,788 | 392,579 | 345,855 | 5,021 | 41,703 |
| Rust | 930 | 191,021 | 175,314 | 639 | 15,068 |
| TypeScript | 858 | 205,602 | 156,031 | 36,817 | 12,754 |
| Go | 102 | 24,670 | 21,646 | 397 | 2,627 |
| YAML | 132 | 12,224 | 10,204 | 1,467 | 553 |
| HCL | 39 | 6,232 | 4,629 | 701 | 902 |
| JavaScript | 203 | 4,852 | 4,570 | 27 | 255 |
| SQL | 272 | 4,613 | 3,125 | 822 | 666 |
| TOML | 93 | 3,211 | 2,875 | 99 | 237 |
| SVG | 332 | 2,773 | 2,636 | 104 | 33 |
| Shell | 18 | 3,086 | 2,370 | 431 | 285 |
| CSS | 11 | 1,605 | 1,476 | 24 | 105 |
| Pan | 2 | 1,303 | 1,264 | 0 | 39 |
| PowerShell | 3 | 1,536 | 1,246 | 187 | 103 |
| Makefile | 2 | 396 | 265 | 62 | 69 |
| Dockerfile | 4 | 340 | 249 | 31 | 60 |
| HTML | 60 | 235 | 215 | 0 | 20 |
| BASH | 1 | 75 | 43 | 19 | 13 |
| Ruby | 1 | 33 | 17 | 12 | 4 |
| Markdown | 215 | 12,931 | 0 | 9,240 | 3,691 |
| Plain Text | 233 | 52,759 | 0 | 52,706 | 53 |

Top language: Python 46.4%. Generated on November 16, 2026. Canonical report: https://octocounts.com/github/BerriAI/litellm/commit/76e45df333c0b021b56ad119c3f3d4a40deedadf?reportId=5d5c3dc7ee671da1b89c11a3e01859883baa1f51b899ec8fdd2f113210571c41&analysis=%7B%22profile%22%3A%22default%22%2C%22ignoredDirs%22%3A%5B%5D%2C%22includeDocs%22%3Afalse%2C%22includeTests%22%3Afalse%2C%22ignoredLanguages%22%3A%5B%5D%2C%22includeGenerated%22%3Afalse%7D

## Reproduce this report

[Reproduce this exact report and configuration](https://octocounts.com/github/BerriAI/litellm/commit/76e45df333c0b021b56ad119c3f3d4a40deedadf?reportId=5d5c3dc7ee671da1b89c11a3e01859883baa1f51b899ec8fdd2f113210571c41&analysis=%7B%22profile%22%3A%22default%22%2C%22ignoredDirs%22%3A%5B%5D%2C%22includeDocs%22%3Afalse%2C%22includeTests%22%3Afalse%2C%22ignoredLanguages%22%3A%5B%5D%2C%22includeGenerated%22%3Afalse%7D).

## Report FAQ

### How many lines of code does BerriAI/litellm have?

BerriAI/litellm has 2,074,295 lines of code, plus 142,736 comment lines and 230,264 blank lines, for 2,447,295 total lines at commit 76e45df333c0 on November 16, 2026. Tests, docs and generated files are excluded under OctoCounts' canonical public options.

### How was the BerriAI/litellm line count measured?

OctoCounts resolved the public GitHub repository to commit 76e45df333c0, downloaded the source archive, counted it with tokei, and cached the report by commit, tokei version, and analysis options.

### What commit was counted for BerriAI/litellm?

This OctoCounts report was generated from main at commit 76e45df333c0 on November 16, 2026.

## Similar repository reports

- [NousResearch/hermes-agent](https://octocounts.com/github/NousResearch/hermes-agent) — Python, 2,171,779 code lines
- [sgl-project/sglang](https://octocounts.com/github/sgl-project/sglang) — Python, 1,903,202 code lines
- [home-assistant/core](https://octocounts.com/github/home-assistant/core) — Python, 1,725,223 code lines
- [unslothai/unsloth](https://octocounts.com/github/unslothai/unsloth) — Python, 1,722,205 code lines
- [vllm-project/vllm](https://octocounts.com/github/vllm-project/vllm) — Python, 1,693,498 code lines
- [pytorch/pytorch](https://octocounts.com/github/pytorch/pytorch) — Python, 2,669,947 code lines

## Related OctoCounts pages

- [Recently analyzed repositories](https://octocounts.com/recent)
- [Popular SLOC reports](https://octocounts.com/popular)
- [Trending GitHub repositories](https://octocounts.com/trending)
- [Hall of Monoliths](https://octocounts.com/hall-of-monoliths)
- [TensorFlow vs PyTorch](https://octocounts.com/compare/tensorflow-vs-pytorch)
- [Django vs Ruby on Rails](https://octocounts.com/compare/django-vs-rails)
- [Laravel vs Django](https://octocounts.com/compare/laravel-vs-django)
- [How to count lines of code in a GitHub repository](https://octocounts.com/docs/count-lines-of-code-github)
- [GitHub SLOC counter guide](https://octocounts.com/docs/github-sloc-counter)
- [Counting methodology](https://octocounts.com/docs/methodology)
- [SLOC and code metrics glossary](https://octocounts.com/docs/glossary)
- [Original research: how filtering changes SLOC counts](https://octocounts.com/research)
- [OctoCounts API docs](https://octocounts.com/docs/api)
- [All OctoCounts guides](https://octocounts.com/docs)
