Sacha Morard is a self-taught technology entrepreneur with a remarkable career trajectory. After initially pursuing music professionally, he pivoted to the tech industry, first as a web designer, then as a developer, and finally as CTO of several prestigious companies. He served as CTO/CIO and Comex member of Le Monde Group for six years, playing a crucial role in the media company's technological advancements.
When he’s not working on the future of tech, Sacha can be found hiking in the mountains, playing the saxophone or guitar, or cooking Neapolitan pizzas in his homemade wood-fired oven.
500 Qonto engineers now run their coding agents through Edgee, and the migration went smoothly over the summer. We asked Kevin Prettre, Director of Infrastructure and Engineer Support at Qonto, why they didn't build it themselves, how they assessed compliance, and what is still hard.
Six gateways, 43 regions, 16,344 measurements. Edgee has the lowest overhead on GPT-5.4 (24ms over a direct API call) and delivers the first token first in two out of three head-to-heads.
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.
Today we're shipping two things: Codex support for the Edgee compressor, and Session Reports.
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.
LLM integrations shouldn’t be a maze of SDKs, provider quirks, and blind spots. Edgee AI Gateway gives you a unified API to ship faster, route smarter, and observe everything — with configurable privacy controls.
Would you like to find out more about Edgee, test our services or our upcoming features? We’d love to hear from you. Please fill in the form below and we’ll be in touch.
