Edgee On-Premise: The Gateway, Behind Your Firewall
The same compress, route, and observe gateway, now deployable entirely inside your own infrastructure.
Edgee Blog: Navigating our innovative Future
Welcome to the official blog of Edgee where our founders and leading thinkers dive deep into the transformative world of edge computing. Here, we explore the latest trends, share groundbreaking innovations, and offer our perspective on the evolving digital landscape. From technical deep dives and industry analyses to visionary outlooks, Edgee Blog is your go-to source for thought leadership in edge computing. Join us as we chart the course towards a more connected, efficient, and innovative future.
Measuring token compression for coding agents on SWE-bench Lite
Compressor V2 is the combination of three independent compression strategies: brevity, tool surface reduction and tool result trimming. Each targets a different layer of an agent's request. This post measures end-to-end the gains of this new composed strategy, on real coding and tool-use workloads with paired statistical tests. The results show a combined 50% per-task cost reduction.
Stop Paying Codex to Re-Read Context
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.
Edgee now compresses OpenAI Codex, and every session tells its own story
Today we're shipping two things: Codex support for the Edgee compressor, and Session Reports.
Retry and Fallback: How Edgee Keeps Your LLM Requests Reliable
LLM providers go down, hit rate limits, and time out. Here's how Edgee handles retries, fallbacks, and provider scoring to keep your requests succeeding, transparently.
We Made Claude Pro Last 26.5% Longer
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.
Bring Your Own Keys: Keep Your Provider Setup and Use Edgee
Bring Your Own Keys (BYOK) lets teams use their own provider API keys with Edgee while benefiting from token compression, routing, observability, and usage tracking.
Edgee in 90 Seconds
A short tutorial video walking you through the essentials of Edgee AI Gateway — what it is, how to get started, and how to route and manage your LLM traffic in under two minutes.
A Cost and Control Layer for Production LLM Systems
Edgee AI Gateway introduces a new operational layer for production LLM systems, built to reduce costs while bringing visibility and control to AI infrastructure.
You Can't Optimize What You Can't See: Why AI Cost Observability Is the Missing Layer
AI costs are rising. The root cause isn't economic—it's operational. Cost observability, meaning real, request-level, attributable cost tracking, is the missing layer. And without it, every other optimization strategy is flying blind.
PreviousNext
Contact us
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.