Otari

What it does

Otari is an LLM gateway and control plane from Mozilla.ai. Applications use a common endpoint while Otari manages provider routing, workspace budgets, API keys, failover and usage records. A dashboard helps teams inspect the model traffic and spending across applications.

It can be hosted by the provider or deployed on the organization’s own infrastructure, with cloud or local models behind it. Developers can use an OpenAI-compatible client or the Otari SDK. Self-hosting involves operating the gateway and configuring provider credentials; a free-start invitation does not establish unlimited hosted inference.

What it can do

• Model routing
• Budget controls
• API-key management
• Workspace governance
• Failover
• Usage analytics

Before you choose

• Model-provider and hosting costs remain separate.
• Hosted free-start limits and production pricing need confirmation.

Listed under

• Coding
• Sandboxes and infrastructure

Get started

1. Choose hosted or self-hosted deployment.
2. Configure model providers, workspace keys and spending limits.
3. Test routing and failover before directing production traffic through the gateway.

The stack can be self-hosted and a hosted free-start option is advertised. Hosted allowances and commercial rates are not specified on the public landing page; model usage and infrastructure have separate costs.

We couldn’t find published prices for Otari. See their pricing page ↗

Sources for this overview

Product pages, documentation, and pricing checked 30 Oct 2026. Each source supports part of the overview; availability and prices can change.

• Otari: Own Your AI Stack | AI Gateway & Hosted Platform ↗otari.ai

Company website

otari.ai: product, pricing and policy pages

Social accounts

Accounts the company links, and its posts on X

Human review

Checked by a person

knowledge_base

manual_review

Last checked 30 Oct 2026. Every field keeps its source and date; unknown means we couldn’t confirm it.