Overview
Edgee is an Agent gateway built to bring LLM and coding-agent costs under control. As engineering teams scale their use of Claude Code, Codex, Cursor, and GitHub Copilot, token spend doubles roughly every six months, and most organizations have no visibility into who is spending what. Edgee sits between your developers and your AI providers, compressing tokens transparently and giving finance and engineering a single, consolidated view of consumption per developer, per squad, and per repository.
Beyond cost observability, Edgee provides intelligent multi-provider routing with automatic fallback. Route inference traffic across Anthropic, OpenAI, Amazon Bedrock, Google Vertex AI, and open-weight frontier models based on cost, performance, and availability, and reroute automatically when a provider hits rate limits or experiences an outage. This eliminates provider lock-in and keeps your developers productive even during incidents. Token compression and routing combined typically deliver 50% or more in token cost reduction.
Edgee is designed for enterprise deployment: it installs in minutes, supports BYOK (bring your own key), integrates with SSO/Okta for team management, and can be self-hosted in your own AWS environment via Helm chart for full data control. It is SOC 2 Type 2 compliant, with no data retention by default. Whether you are running a FinOps initiative, preparing for usage-based provider pricing, or simply trying to make AI spend predictable, Edgee turns an unpredictable, fast-growing cost line into a managed one.
Highlights
- Reduce coding-agent token costs by up to 50% with transparent token compression and smart routing to cost-efficient models, with no change to how your developers work.
- Gain complete cost observability across your AI usage: track and attribute token spend per developer, per team, and per repository in real time, the visibility most organizations lack today.
- Eliminate provider lock-in and downtime with multi-provider routing and automatic failover across Anthropic, OpenAI, Amazon Bedrock, and open-weight models. Self-hosted deployment available for full data control.
Details
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
Pricing
Dimension | Description | Cost/month | Overage cost |
|---|---|---|---|
freerequests | The first 3 million requests are free every month. | $0.00 | - |
freecollectionevents | The first 3 million events are free every month. | $0.00 | - |
Developer Seat Standard | Monthly license for one developer on the Standard tier. Includes token compression across all coding agents (Claude Code, Codex, Copilot, Cursor, OpenCode), BYOK with a daily token allowance on Edgee models, fallback and rerouting, team observability, per-seat spending caps, and GitHub per-repo and per-PR attribution. | $29.00 | |
Developer Seat Pro | Monthly license for one developer on the Pro tier. Includes everything in Standard, with a substantially higher daily token allowance on Edgee models for heavy daily users. | $99.00 | |
Developer Seat Max | Monthly license for one developer on the Max tier. Includes everything in Pro, with the highest token allowance for power users running coding agents continuously. | $199.00 | |
Private Gateway License | Annual license for a dedicated Edgee gateway, hosted by Edgee or self-hosted in your own infrastructure via Helm chart. Includes SSO/SAML, custom data residency (EU or US), custom privacy controls, and a contractual SLA with dedicated support. | $1,500.00 | - |
The following dimensions are not included in the contract terms, which will be charged based on your usage.
Dimension | Description | Cost/unit |
|---|---|---|
requests1 | Price per million for 3 - 5 million requests. 1 million is 1 Unit. | $2.40 |
requests2 | Price per million for 5 - 10 million requests. 1 million is 1 Unit. | $1.96 |
requests3 | Price per million for 10 - 35 million requests. 1 million is 1 Unit. | $1.53 |
requests4 | Price per million for 35 - 50 million requests. 1 million is 1 Unit. | $1.09 |
requests5 | Price per million for 50 - 100 million requests. 1 million is 1 Unit. | $0.65 |
requests6 | Price per million for 50 - 100 million requests. 1 million is 1 Unit. | $0.44 |
requests7 | Price per million for 500 - ... million requests. 1 million is 1 Unit. | $0.38 |
collectionevent1 | Price per million for 3 - 5 million data collection events. 1 million is 1 Unit. | $66.47 |
collectionevent2 | Price per million for 5 - 10 million data collection events. 1 million is 1 Unit. | $53.44 |
collectionevent3 | Price per million for 10 - 35 million data collection events. 1 million is 1 Unit. | $40.40 |
Vendor refund policy
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
Software as a Service (SaaS)
SaaS delivers cloud-based software applications directly to customers over the internet. You can access these applications through a subscription model. You will pay recurring monthly usage fees through your AWS bill, while AWS handles deployment and infrastructure management, ensuring scalability, reliability, and seamless integration with other AWS services.
Support
Vendor support
Email: support@edgee.ai
Support URL: https://www.edgee.ai/docs
Enterprise customers receive priority support with direct access to our engineering team, onboarding assistance for gateway deployment (SaaS or self-hosted via Helm chart), and configuration support for compression, routing, and observability. Documentation, integration guides, and best practices are available at
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.