Providers · Beta

Keep Claude API spend within hard limits.

Add your Anthropic API key once. Give each app an approved Claude model, a hard spending limit, and a compatible fallback.

Create a free workspace Try the no-card Test Lab

How the connection works

How Anthropic works with the gateway

Keep the Messages API shape

Apps send Anthropic Messages requests to the gateway with a workload key and model alias. The gateway applies the approved app, route, model, and provider account before it calls Anthropic.

Rotate one provider key

The Anthropic credential stays encrypted and write-only. Replace it centrally instead of copying a new provider key to every developer machine and service.

Use only a compatible fallback

Health, quota, budget, policy, and capability checks determine whether a target can receive the request. A fallback must support the same request shape and streaming mode.

Current shared controls

What every supported connection includes

Encrypted BYOK credentials that remain hidden after setup Stable model aliases and compatible route targets Organization and key budgets, rate limits, and concurrency limits Observe, Shadow, and Enforce modes with metadata-only evidence

Test the exact Claude model, Messages payload, streaming mode, and provider account as part of the production review.

Client boundary

AIGHQ_BASE_URL=https://api.aigatewayhq.com/v1
AIGHQ_API_KEY=from-your-workspace
AIGHQ_MODEL=company-approved-fast

Applications keep a stable gateway URL and model alias for Anthropic. Administrators can change eligible Anthropic accounts and models centrally.

Implemented boundary

Supported protocols

Select Anthropic and enter the API key once. The connection test checks account access and does not generate tokens. Then map each app to a stable model alias.

POST /v1/messages Anthropic-compatible streaming GET /v1/models connection test

Compatibility follows the provider's current published interface. Review the provider documentation before approving Anthropic for production.