For inference providers

List your models on TrustedRouter.

Give us stable machine interfaces once. We will validate your routes, publish your models, monitor availability, and keep pricing current.

Email providers@trustedrouter.com View requirements

1dedicated API key

3machine-readable URLs

Hourlycatalog refresh

ConnectSend a restricted key and API base URL.

DiscoverExpose live models through a catalog endpoint.

PricePublish exact rates through a pricing API.

VerifyWe test, monitor, and list working routes.

Send one email

Everything needed to connect.

Email providers@trustedrouter.com from your company domain. Include a technical contact who can answer routing and pricing questions.

Dedicated API key. A revocable production key scoped to inference and model discovery.
Inference API URL. The HTTPS base URL used to call your models, plus authentication and API documentation.
Models API URL. A machine-readable endpoint such as GET /v1/models with stable model IDs and current availability.
Pricing API URL. A machine-readable endpoint with exact input, output, cache, and other billable rates.

Never send an account password, owner credential, billing credential, or unrestricted administrative key.

Email checklistproviders@trustedrouter.com

Company:
Technical contact:

API base URL:
API documentation:
Authentication format:
Dedicated API key:

Models API URL:
Pricing API URL:

Supported features:
Regions:
Retention policy URL:
Confidential compute URL:
Deprecation feed or contact:

Machine readable by design

Make launches and price changes automatic.

Web pricing pages are useful for people. TrustedRouter also needs structured sources that software can ingest without guessing.

Inference

A stable API base URL.

OpenAI compatibility is preferred. Document chat, Responses, streaming, tools, vision, embeddings, timeouts, and rate-limit behavior where supported.

https://api.provider.com/v1

Catalog

A live models endpoint.

Return stable model IDs, availability, context length, maximum output, modalities, and capabilities. Include pagination when needed.

GET /v1/models

Pricing

An exact pricing endpoint.

Return currency, units, input and output rates, cache read and write rates, minimum charges, tiers, and effective timestamps as exact decimals.

GET /v1/pricing

After the email

We verify before we list.

Validate authentication and retrieve the live model catalog.
Match model IDs to exact prices and supported capabilities.
Run non-streaming and streaming probes against representative models.
Publish provider and model pages only for callable routes.
Refresh availability and pricing automatically as your APIs change.

Also include

Help developers choose your routes.

Data retention, training, and zero-retention policy links
Confidential-compute or attestation documentation
Serving regions and data-residency constraints
Rate limits, capacity tiers, and expected error contracts
A machine-readable deprecation feed, or an operations contact

Ready to connect?

Send the integration details and dedicated key to providers@trustedrouter.com.

Start provider integration

Questions

What API format works best?

An OpenAI-compatible HTTPS API is the fastest path. Include the inference base URL, authentication format, supported request types, streaming behavior, and any model-specific capability differences.

Why do you require model and pricing APIs?

TrustedRouter refreshes provider catalogs automatically. Machine-readable model availability and pricing let us add launches, update prices, and remove retired routes without relying on stale web pages or manual email updates.

What kind of API key should we send?

Create a dedicated, revocable production key scoped only to inference and model discovery. Do not send an account password, owner credential, billing credential, or unrestricted administrative key.