# Edgee Blog Category: Performance

### [Stop Paying Codex to Re-Read Context](/content/blog/posts/stop-paying-codex-to-re-read-context/index.html)

We benchmarked Codex alone against Codex routed through Edgee's compression gateway on the same repo, with the same model, under the same workflow. The result: Codex + Edgee used 49.5% fewer input tokens, improved cache hit rate from 76.1% to 85.4%, and reduced total session cost by 35.6%. This post breaks down why context compression makes Codex more efficient, more frugal, and materially cheaper to run without sacrificing useful output.

\
\
Sacha Morard\
\
co-founder co-CEO](/content/blog/authors/sacha-morard/index.html)

### [We Made Claude Pro Last 26.5% Longer](/content/blog/posts/2026-03-19-claude-code-endurance-challenge/index.html)

We ran a head-to-head endurance test: raw Claude Code vs Claude Code with Edgee's token compressor. Same plan, same tasks. One went 26.5% further.

\
\
Sacha Morard\
\
co-founder co-CEO](/content/blog/authors/sacha-morard/index.html)