Providers · Beta

Put Together AI models behind stable, governed workload aliases.

First-class Together BYOK with the official API base, model-catalog verification, Chat Completions, and embeddings eligibility.

Start in a test environment Read current API behavior

How the connection works

Provider access stays separate from application control.

Preserve the namespaced model boundary

Together model identifiers include the provider and model name. The gateway maps a reviewed identifier to a stable company alias, allowing applications to keep one client configuration while administrators change only compatible targets.

Separate chat from embeddings

Chat Completions and embeddings share an OpenAI-compatible surface but are not interchangeable workloads. Route validation keeps their target eligibility explicit, and each application can have its own budget, rate, concurrency, and environment boundary.

Verify before paid inference

The connection test reads the model catalog rather than generating a response. Administrators can confirm the credential, review the selected target, and simulate the policy path before allowing the workload to consume provider tokens.

Current shared controls

Status determines what can be configured.

Write-only, encrypted BYOK for implemented provider connections Stable model aliases and protocol-eligible route targets Organization and key budgets, RPM, TPM, and concurrency hard limits Observe, Shadow, Enforce, reason codes, and metadata-only evidence

Beta connections require customer validation against the exact model, payload, streaming mode, region, and provider account before production use.

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 while an administrator changes eligible provider accounts and models.

Implemented boundary

Only documented protocols become eligible.

Choose Together AI, enter the write-only API key, verify it without inference, and use Together's namespaced model identifier in the route.

POST /v1/chat/completions POST /v1/embeddings GET /v1/models connection test

Compatibility is bounded to the provider's current published interface. Review the provider documentation before approving a production model.