less-tokens
Cut LLM prompt token costs by 30-40% with deterministic, training-free lexical compression. Shrink prompts for OpenAI, Anthropic, and any LLM API while preserving output quality. Includes zone-aware compression that protects JSON schemas and output formats, async support, and a built-in 6-metric quality evaluator.
less-tokens has been downloaded 5,977 times in total on PyPI, including 4,710 in the last 30 days. The latest version is 0.2.0, released May 20, 2026. It is distributed under the MIT license.
Downloads
Weekly, last 90d.
Includes CI traffic.
Sponsorships keep pepy free to read
Version distribution
Share of downloads by released version. Computed over the last quarter.
- 019.7%
0.4.0
578 downloadsDownloads5789.7% - 028.9%
0.1.0
534 downloadsDownloads5348.9% - 038.4%
0.2.0
502 downloadsDownloads5028.4% - 048.2%
0.6.1
488 downloadsDownloads4888.2% - 057.9%
0.5.1
475 downloadsDownloads4757.9% - 067.8%
0.5.0
468 downloadsDownloads4687.8% - 077.8%
0.6.5
467 downloadsDownloads4677.8% - 087.7%
0.6.0
463 downloadsDownloads4637.7% - 0933.5%
Other
2.0k downloadsDownloads2.0k33.5%
Guess the next day
Thirteen recent days of less-tokens downloads. Drag the green handle on the right to guess where day fourteen lands.