Edgee Claude Code Compressor

Extend Claude Pro's limit by 26.2%

Website edgee.ai

What it is

Edgee compresses prompts before they reach LLM providers and reduces token costs by up to 50%. Same code, fewer tokens, lower bills.

Intent

I need it when

Track and optimize LLM spending per developer, repository, and pull request

Team plan includes centralized dashboard with cost attribution by repo/PR, usage exports, spending alerts, and per-request compression metrics (saved_tokens, cost_savings, reduction %). GitHub integration enables per-repo and per-PR attribution. All plans include session-level metering.

Scale coding agent infrastructure across team with security and compliance controls

Team plan (€29/developer/month) provides unlimited organization members, admin-provisioned keys, centralized key management, and GitHub integration. Enterprise plan adds SSO/SAML, audit logs, custom data residency (EU/US/private), and self-hosted deployment options.

Ensure coding agent continues working when primary LLM provider fails or hits rate limits

Automatic per-request fallback and retry across 200+ models with configurable provider chains. Retries transient errors (429, 5xx) once before moving to next provider. Plan-cap continuity for Claude Pro/Max users when quota exhausted. Zero downtime from agent perspective.

Maintain billing control and use custom LLM provider accounts with routing benefits

Bring Your Own Keys (BYOK) feature lets users register own API keys for Anthropic, OpenAI, Google Vertex AI, Mistral, DeepSeek, xAI, zAI, and AWS Bedrock. Requests route through user's key and billing account while Edgee compression, routing, and observability continue working.

Reduce LLM token costs and extend coding session duration without modifying agent code

Edgee compresses input and output tokens by up to 50% through surgical removal of redundancy (tool-result trimming, tool-surface reduction, output brevity). Works as transparent proxy for Claude Code, Codex, Cursor, and OpenCode—no code changes required. Extends sessions by up to 26.5% on same plan.

Drop

Not a fit when

User requires on-premises deployment without custom enterprise agreement (self-hosted only available on Enterprise plan)
User needs real-time token compression for non-coding LLM workloads (product optimized for coding agents: Claude Code, Codex, Cursor, OpenCode)
User operates in regions requiring data residency outside EU/US without custom enterprise setup
User requires sub-second latency guarantees (gateway adds measurable overhead despite edge processing)
User needs compression for streaming responses already in-flight (retries only possible before first chunk sent)

Commercials

Pricing

Freemium with team and enterprise tiers. Free plan includes token compression for solo developers. Team plan at €29/developer/month (billed annually) adds fallback, rerouting, and team management. Enterprise plan offers custom pricing with SSO, audit logs, and self-hosted options. View pricing