Skip to content
Halo by OmniTrust

Model providers

Available now

Halo and Anthropic

Bring Anthropic model access under Halo gateway policy, credential, budget, and evidence controls.

Book a walkthrough Start with Halo

How Halo works with Anthropic

Halo routes approved Anthropic model requests through the model gateway, applying configured identity, policy, budgets, and evidence controls to agent traffic.

Anthropic is a supported BYOK provider. Halo keeps the provider credential bound at the gateway while agents receive scoped capabilities.

Governance

What Halo governs for Anthropic

Model access

Route approved Anthropic model requests through Halo’s model gateway.

Request and response checks

Evaluate model traffic against configured policy in supported gateway paths.

Credential brokering

Keep provider credentials at the gateway so agents do not receive raw keys.

Budget and evidence

Set account or agent budgets and retain reviewable records of decisions and costs.

Example agent jobs

Put agents to work with Anthropic

Illustrative jobs. Each one runs with scoped access, policy, and evidence.

Illustrative research summary

For example, an agent could prepare a research summary with an approved Anthropic model, subject to configured policy and budget controls.

Illustrative document review

For example, an agent could draft a review note from approved input, with a person approving any higher-impact follow-up action.

Setup

Get connected in three steps

  1. 1

    Select Anthropic

    Choose Anthropic from the available provider options in the model gateway.

  2. 2

    Configure BYOK

    Bind the provider credential through Halo’s gateway so the agent uses scoped model access.

  3. 3

    Apply governance

    Select an approved model, set policy and budget controls, and test the agent workflow.

FAQ

Questions, answered

Yes. Anthropic is a supported BYOK provider, with the credential brokered through the Halo gateway.

Supported gateway paths can evaluate model requests and responses under configured policy and record reviewable decisions.

Related capabilities

Model GatewayManaged and BYOK model accessLearn more about Model GatewayModel RoutingRoute requests to the right approved modelLearn more about Model RoutingRuntime GuardrailsDetect sensitive data and injectionLearn more about Runtime Guardrails

More model providers

Put a halo around the AI your business runs.

See discovery, runtime policy, approvals, and evidence working together on your own use cases.

Book a walkthrough Start with Halo