Charge your users for the AI they use.

Call leading models through one API. ModelRelay meters every request to the customer who made it.

Early access

Provider rates pass straight through at a 0% ModelRelay fee, and every new account starts with $1 in credit.

Model requestcompleted
POST /api/v1/responses
01 · customer authorizedPro
02 · model routedclaude-sonnet-5
03 · usage recorded1,248 tokens
04 · cost attributed[email protected]
One requestone attributable usage record

Models · API · Monetize

01

Models

Speed, cost, intelligence.

Rank models by what matters to you.

Tune the balance between speed, cost, and intelligence, then inspect the same model you can call through the API.

Current benchmarks

Every model runs the same controlled task, with output and performance you can inspect.

Visible tradeoffs

See serving speed, provider pricing, and independently sourced intelligence together.

Switch without a rewrite

Move to a different model by changing one string, not by rebuilding around another provider.

Explore models and tune the ranking
02

API

One request shape.

Integrate once. Keep model choice open.

Use ModelRelay's provider-neutral Responses API, or point an existing OpenAI or Anthropic integration at the compatible endpoints.

See how requests flow
Call a model
ModelRelay · POST /api/v1/responses Drop-in · OpenAI /v1/responses · Anthropic /v1/messages
curl https://api.modelrelay.ai/api/v1/responses \
-H "Authorization: Bearer $MODELRELAY_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"claude-sonnet-5","input":"Hello"}'

Change the model. Keep everything else.

03

Monetize

Usage in. Revenue out.

Every model call, accountable and billable.

Know who made each request, what it cost, and what their plan allows.

Customer identity

Use customer tokens to attribute requests and usage to the right end user.

Tiers and budgets

Define plans, approved models, credits, and spend limits in one control plane.

Your price, your margin

Set customer pricing while ModelRelay keeps the underlying provider cost attributable.

Explore AI monetization
Available today

From model request to customer ledger.

ModelRelay combines model access, request controls, usage accounting, and customer billing in one hosted API.

01 · Authorize

Validate the project or customer token.

02 · Route

Send the request to the model's provider.

03 · Meter

Record returned usage and available provider cost.

04 · Attribute

Apply usage to the correct customer and plan.

Ship AI features with the billing already attached.

ModelRelay is invite-only while we onboard early teams. Pay by card or USDC.

You are on the list.We will email .