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 8,006 times in total on PyPI, including 3,210 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.
- 0112.2%
0.7.0
980 downloadsDownloads98012.2% - 027.6%
0.4.0
612 downloadsDownloads6127.6% - 037.3%
0.6.7
582 downloadsDownloads5827.3% - 047.0%
0.1.0
563 downloadsDownloads5637.0% - 056.7%
0.6.5
538 downloadsDownloads5386.7% - 066.6%
0.2.0
531 downloadsDownloads5316.6% - 076.6%
0.6.1
530 downloadsDownloads5306.6% - 086.4%
0.5.1
511 downloadsDownloads5116.4% - 0939.5%
Other
3.2k downloadsDownloads3.2k39.5%
Guess the next day
Thirteen recent days of less-tokens downloads. Drag the green handle on the right to guess where day fourteen lands.