OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI APIs & Platforms

Mozilla AI

Otari is an LLM gateway and policy layer that gives applications a unified API for accessing models from multiple providers, while workspaces manage provider connections, model access, API keys, usage and budgets.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Mozilla AI — OpenViST project profile in AI APIs & Platforms.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use hosted Otari when you want to manage model access and usage without running the gateway yourself; consider the self-hosted documentation when the runtime needs to operate in your own infrastructure.

Who it is for

  • Teams connecting applications or coding agents to models from multiple providers.
  • Organizations that want workspace-scoped access, usage reporting and spending controls.
  • Teams choosing between a hosted gateway and a runtime in their own infrastructure.

Documented uses

  • Send application requests to different models through a unified API.
  • Manage provider credentials and decide which workspaces can access them.
  • Review request usage and apply budgets to monitor spending.
Before you choose

Requirements & limits

The hosted offering is presented with a free starting option and usage-based payment. The gateway is described as open source, and self-hosted documentation is available.

  • Hosted Otari avoids running the gateway; self-hosted operation is documented separately.
  • Workspace API keys and model selection are part of the hosted request flow.
  • EU-region accounts must use the EU API hostname rather than the standard hostname.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Prepare a hosted Otari model request

Set up the documented workspace elements and choose the API base URL for a hosted integration.

Before you start

  • An Otari hosted workspace
  • A workspace API key
  • A model selected in the workspace

Steps

  1. Create a workspace API key.

  2. Select a model.

  3. Send the application request to https://api.otari.ai/api/v1.

  4. If the account is in Otari’s EU region, use https://eu.api.otari.ai/api/v1 instead.

Expected outcome

The application has the workspace key, selected model and regional API base URL needed for the documented request flow.

Guide limitations

  • The documentation says the standard API hostname returns a 421 Misdirected Request for an EU-region key.
  • Request payload details and execution results are not covered by this setup guide.
Documentation 1 ↗Documentation 2 ↗
Evidence and transparency

Sources & review

otari.ai ↗Guide documentation ↗
Source record details
Source availability
Active
Sources checked
5 November 2026
Original website title
Otari by Mozilla AI: open-source AI gateway for any model · Official homepage title · retained in its source language
How we review sourcesSuggest a correction