GoModelPRO

The core stays free - Pro is how it stays sustainable.

Read the Pro docs

Early offer

One price. One company. Nothing counted.

$4,999per yearPay yearly and two months are on the house.Buy annual →or$499per monthCancel whenever you like.Buy monthly →
  • Unlimited requests, seats, nodes, environments, and providers. The license is per company, and it never phones home.
  • 30-day money-back guarantee. So there is no risk.
  • Founder-level support (early offer only) - direct access to the person who wrote the code.
  • Your license key arrives by email within 24 hours - sent by a real human.
  • Every Pro feature shipped during your term is included - see the roadmap.
  • Renew and your price is locked.
  • We will be proud to place your logo on our website - if you would like it there.

Checkout is by Stripe: card, Apple Pay, or US bank debit, with VAT IDs, billing details, and invoices handled there. Buying accepts the Commercial License Agreement. Already a customer? Manage billing - invoices, card, cancellation.

Free versus Pro

Almost every row below is identical, and that is the point. The open-source gateway is not a demo of the paid one.

CapabilityGoModel (MIT)GoModel Pro
The gateway itself
Providers, model aliases, virtual modelsAll of themAll of them
OpenAI and Anthropic compatible endpointsIncludedIncluded
Caching, failover, load balancingIncludedIncluded
Budgets, rate limits, virtual keysIncludedIncluded
Audit logs, usage and cost trackingIncludedIncluded
Admin dashboard, MCP gateway, guardrailsIncludedIncluded
OpenTelemetry traces and metricsIncludedIncluded
Requests, seats, nodes, environmentsUncappedUncapped
LicenseMIT, foreverCommercial, on top of the same MIT core
What the license adds
Prompt compressionNot included2-20% fewer input tokens on agentic traffic
OIDC single sign-onAPI keys onlyAuthorization Code + PKCE, group-gated, audited
Per-child quota templatesOne shared subtree budgetOne rule, an independent budget per child path
Intelligent routingRound robin and cheapest-costEasy/hard tiering + adaptive selection (beta)
SupportDiscord and GitHub issuesFounder-level support (early offer)

Without a license the Pro binary starts as the open-source gateway and keeps serving traffic. The one exception is single sign-on: if you explicitly enable it and the entitlement is invalid, startup fails closed, because an authentication boundary must never disappear quietly.

What the license actually turns on

The full list is in the table above. Intelligent routing is in beta and described further down, without the marketing voice.

Prompt compression

Saves you between 2-20% of input tokens on agentic traffic. Nothing is summarized, nothing is dropped, and prompt caches keep hitting.

Documentation

OIDC single sign-on

Okta, Entra ID, Google, Auth0, or Cognito in front of the dashboard. Deploy the gateway org-wide instead of key-by-key.

Documentation

Founder-level support (early offer)

Direct access to the person who wrote the code.

About that 2-20% number

Compression removes 2% to 20% of input tokens depending on the traffic: long agent sessions that replay files and tool output sit at the top, short chat at the bottom. Requests below the thresholds pass through unchanged.

Short, non-repetitive chat
2%
Average across 12 public agent transcripts
8%
Long agentic sessions
20%
119-request coding session (measured)
24.5%

Input tokens removed, by traffic shape. Output tokens are untouched.

GoModel dashboard Usage Analytics over seven days: 7,145 requests, $268.63 estimated cost, Pro saved $45.17 - 14.4% less
Seven days of one customer's production traffic, straight from the dashboard: $45.17 saved on a $268.63 bill.

Every rewrite is visible in response headers, audit revisions, metrics, and the dashboard's own savings figure. And if Pro is not for you, there is the 30-day money-back guarantee.

Beta

Intelligent routing

A deterministic tier router scores each request on signals like reasoning parameters, code fences, and context size, then sends it to an easy or hard model tier. An adaptive selector picks the healthiest, cheapest target inside that tier from live latency and error data. Every verdict is explainable in response headers and the audit trail.

RequestTier routerscores each requestEasy tierHard tierAdaptive selectorcheapest healthy target

Included in the license and working, but beta: routing state is per node rather than shared across a cluster, and streaming latency is measured to stream establishment. Turn it on first for a workload where a wrong tier is cheap.

Routing documentation

What Pro deliberately is not

Not metered

Nothing counts your requests, seats, nodes, or spend. License validation is an offline signature check - it works air-gapped.

Not a hostage situation

Stop paying and the binary keeps running. The open-source gateway keeps every feature it has today.

Not an enterprise sales motion

The price is on this page. There is no call you have to sit through to learn it.

Still deciding?

Run the open-source gateway first - it is a single binary and it takes a minute. When compression, single sign-on, or per-tenant budgets become the thing standing between you and shipping, come back.

Get GoModel ProBook a 30-minute call
Get GoModel Pro