The AI Gateway that TL;DR tokens
Edgee compresses prompts before they reach LLM providers.
Same code, fewer tokens, lower bills.
curl https://api.edgee.ai/v1/chat/completions -d \
'{
"model": "gpt-4o",
"message": "A long prompt and tool calls that could be optimized..."
}'Backed by founders and leaders of
Token Compression & Cost Governance
Use powerful models at a fraction of the cost
Edgee optimizes your prompts at the edge using intelligent token compression, removing redundancy while preserving meaning. The compressed requests are then forwarded to your LLM provider of choice. Tag requests with custom metadata to track usage and costs, and get alerted when costs spike, before they become a problem.
Up to 50% input token reduction
Reduce LLM costs by intelligently compressing prompts at the edge.
Semantic preservation
Preserves context and intent while removing redundant tokens.
Universal compatibility
Works with any LLM provider, including OpenAI, Anthropic, Gemini, xAI, and Mistral.
Cost governance
Tag requests with custom metadata to track usage and costs, and get alerted when spending spikes.
await edgee.send({
model: 'openai/gpt-4',
input: 'Generate report',
tags: ['feature:reports', 'team:analytics']
});How it works
One gateway, many providers
Your application calls Edgee. We apply policies at the edge (routing, privacy controls, retries), then forward the request to the best provider for the job.
- Normalize responses across models so you can switch providers easily
- Observe and debug production AI traffic end-to-end
- Control costs with routing policies and caching
import Edgee from 'edgee';
const edgee = new Edgee('your-edgee-api-key');
const res = await edgee.send({
model: 'openai/gpt-5.2',
input: 'Explain edge computing like I’m 5',
});
console.log(res.text);Why Edgee AI Gateway?
An edge intelligence layer for your AI traffic
Edgee sits between your application and LLM providers behind a single OpenAI-compatible API. It adds edge-level intelligence, including token compression, routing policies, cost controls, private models, and tools, so you can ship AI features faster and with confidence.
Token compression
Reduce prompt size without losing intent to lower costs and latency, especially for long contexts, RAG pipelines, and multi-turn agents.
Learn moreEdge Tools
Invoke shared tools managed by Edgee, or deploy your own private tools at the edge, closer to users and providers for lower latency and tighter control.
Learn moreBring Your Own Keys
Use Edgee’s keys for convenience, or plug in your own provider keys for billing control and custom models.
Learn moreObservability
Monitor latency, errors, usage, and cost per model, per app, and per environment.
Learn moreEdge Models
Run small, fast models at the edge to classify, redact, enrich, or route requests before they reach an LLM provider.
Learn morePrivate Models
Deploy serverless open-source LLMs on demand, where you need them, and expose them through the same gateway API alongside public providers.
Learn moreThe vision behind Edgee
Every technological shift creates a new foundation: the web had bandwidth, the cloud had compute, and AI has tokens. In a world powered by models, intelligence has a cost: tokens flow through every interaction, decision, and response.
At Edgee, we believe intelligence should move efficiently, closer to users, intent, and action. It should be compressed, routed, and optimized so decisions happen instantly. Hear from Sacha, Edgee’s co-founder, on how AI scales by mastering how intelligence moves.