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 8,822 times in total on PyPI, including 1,221 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.
- 0113.0%
0.7.0
1.1k downloadsDownloads1.1k13.0% - 027.9%
0.4.0
644 downloadsDownloads6447.9% - 037.8%
0.6.7
635 downloadsDownloads6357.8% - 047.0%
0.6.5
572 downloadsDownloads5727.0% - 056.9%
0.6.1
565 downloadsDownloads5656.9% - 066.8%
0.7.1
553 downloadsDownloads5536.8% - 076.6%
0.5.1
542 downloadsDownloads5426.6% - 086.6%
0.6.0
536 downloadsDownloads5366.6% - 0937.5%
Other
3.1k downloadsDownloads3.1k37.5%
Guess the next day
Thirteen recent days of less-tokens downloads. Drag the green handle on the right to guess where day fourteen lands.