Free
Free
One developer; provider usage extra
- Included scope
- Gateway, rerouting and personal reporting
Edgee
● Identity checkedAgent model gateway budgets and cost attribution · Official-source review 2026-10-09
Edgee routes coding-agent requests through configurable model policies, compression and usage reporting. It advertises provider fallback and cost attribution by developer, repository and pull request, with team controls on paid plans.
- Category
- Agent model gateway budgets and cost attribution
- Free access
- Free one-developer platform tier. Provider tokens extra; credit top-ups carry5% fee on Free, none on Team/Enterprise; BYOK commission0%.
- API access
- OpenAI/Anthropic-compatible API, SDK connections and coding-agent CLI advertised. GitHub attribution and plugins on Team.
Is Edgee right for you?
A good fit for
Relevant to engineering teams reconciling request costs and testing budget-triggered routing.
Before you choose
Team $30/developer/month excludes model tokens; Enterprise negotiated private gateway/model hosting and identity. Hosted private open models can bill GPU-hour. Smart task routing beta; self-learning coming soon. Budget-routing headline on Free differs from spend-caps/alerts Team matrix. Mid-task model changes and compression can alter answers despite no-quality-loss/70%savings claims. On-prem gateway still sends data to external providers unless inference also local or contracted otherwise. Existing subscription compatibility needs provider terms. No gateway request, compression, attribution or failover test performed.
Workflow and handoff
Replay safe coding requests, inspect context changes and route choices, then reconcile costs before applying team budget rules.
Pricing and practical limits
Team $30/developer/month excludes model tokens; Enterprise negotiated private gateway/model hosting and identity. Hosted private open models can bill GPU-hour. Smart task routing beta; self-learning coming soon. Budget-routing headline on Free differs from spend-caps/alerts Team matrix. Mid-task model changes and compression can alter answers despite no-quality-loss/70%savings claims. On-prem gateway still sends data to external providers unless inference also local or contracted otherwise. Existing subscription compatibility needs provider terms. No gateway request, compression, attribution or failover test performed.
Review method
Official product evidence reviewed on 2026-10-09; product artwork inspected visually. No hands-on vendor application test was performed. Application performance, security claims and plan enforcement were not independently tested.
What it can do
Features & capabilities
Unknown is different from unavailable. Each fact carries its own evidence.
| Capability | Value | Evidence | Checked |
|---|---|---|---|
| Product workflow | Edgee routes coding-agent requests through configurable model policies, compression and usage reporting. It advertises provider fallback and cost attribution by developer, repository and pull request, with team controls on paid plans. | Facts sourced | 2026-10-09 |
| Pricing and restrictions | Team $30/developer/month excludes model tokens; Enterprise negotiated private gateway/model hosting and identity. Hosted private open models can bill GPU-hour. Smart task routing beta; self-learning coming soon. Budget-routing headline on Free differs from spend-caps/alerts Team matrix. Mid-task model changes and compression can alter answers despite no-quality-loss/70%savings claims. On-prem gateway still sends data to external providers unless inference also local or contracted otherwise. Existing subscription compatibility needs provider terms. No gateway request, compression, attribution or failover test performed. | Facts sourced | 2026-10-09 |
Understand the total cost
Edgee pricing & plans
Team
$30.00 /mo
Per developer/month; tokens extra
- Included scope
- Team policies, plugins and GitHub attribution
Enterprise
Not listed
Custom; private model hosting may bill GPU-hour
- Included scope
- Identity, private gateway and support
Alternatives to Edgee
View all ↗
AurikoAuriko provides an OpenAI-compatible model gateway with provider routing, fallback, key orchestration and cost analytics. It supports user-supplied or platform keys and configurable objectives such as cost, latency and data policy.
Explore tool
Progress Agent EngineeringProgress Agent Engineering traces model calls, prompts, retrieval and tools, then connects costs and failures to evaluations and experiments. Native .NET, Python and TypeScript support helps teams investigate production agent behavior and review governance controls.
Explore tool
ArambAramb combines model routing, voice, browser execution, sandboxes, memory, tool integrations and usage billing for AI-agent products. It supports no-code authoring and developer integration within a shared credit system.
Explore toolThe practical questions
Frequently asked questions
Was the application hands-on tested?
No. This listing is based on dated official-source evidence and a visual artwork check. Unconfirmed costs and restrictions are identified explicitly.
What is Edgee used for?
Edgee routes coding-agent requests through configurable model policies, compression and usage reporting. It advertises provider fallback and cost attribution by developer, repository and pull request, with team controls on paid plans.
Does Edgee have a free plan?
Free one-developer platform tier. Provider tokens extra; credit top-ups carry5% fee on Free, none on Team/Enterprise; BYOK commission0%.. This record lists ongoing free access; check the plan limits before starting.
How much does Edgee cost?
The listed monthly price is $30.00 USD at monthly billing. See the plan cards for entitlements, billing commitments and seat minimums.
Can I use Edgee through an API?
OpenAI/Anthropic-compatible API, SDK connections and coding-agent CLI advertised. GitHub attribution and plugins on Team.. API access and subscription access may have different terms; consult the linked sources.
What should I check before choosing it?
Team $30/developer/month excludes model tokens; Enterprise negotiated private gateway/model hosting and identity. Hosted private open models can bill GPU-hour. Smart task routing beta; self-learning coming soon. Budget-routing headline on Free differs from spend-caps/alerts Team matrix. Mid-task model changes and compression can alter answers despite no-quality-loss/70%savings claims. On-prem gateway still sends data to external providers unless inference also local or contracted otherwise. Existing subscription compatibility needs provider terms. No gateway request, compression, attribution or failover test performed.
Price history
No retained pricing changes yet. A current price alone does not establish a historical trend.
How this profile is supported
Official product information
Current official product source read individually; product artwork inspected visually.
Read original source ↗Pricing review
Official pricing and billing restrictions read individually.
Read original source ↗Facts apply to the named version and check date. Send a sourced correction if something changed.