Magento 2 AI Review TranslatorMagento 2 AI Review Translator
Live Demo
Buy Now
Support
Live Demo
Buy Now
Support
  • Getting Started

    • Introduction
    • Key Features
    • How It Works
  • Installation

    • Requirements
    • Install the Module
    • Install the AI Packages
    • Enable & Compile
    • Verify the Installation
    • Content Security Policy
    • Translating the Interface
  • Setup

    • Enable the Module
    • Activate Your Licence
    • Select an LLM Provider
    • Validate & Load Models
    • First Translation
  • Configuration

    • Overview
    • General Settings
    • Limits & Timeouts
    • Store Views & Languages
    • Admin Menu
    • Access Control
  • LLM Providers

    • Provider Overview
    • How Validation Works
    • Choosing a Model
    • Switching Providers
  • Ollama (Self-Hosted)

    • Install Ollama
    • Connect to Magento
    • Timeouts & Batch Size
    • Troubleshooting
  • Translating Reviews

    • Translation Basics
    • What Is Sent to the Model
    • Fallback Behaviour
    • Automatic Translation
    • The Queue Consumer
    • Running the Consumer
    • Bulk CLI Command
    • Batch Size
    • CLI Output & Exit Codes
  • Storefront

    • On the Storefront
    • The Toggle
    • Styling
  • Developers

    • GraphQL API
    • Querying from Code
    • Data Model
    • Useful SQL
  • Help

    • Setup Problems
    • Translation Problems
    • Queue Problems
    • Storefront Problems
    • FAQ

Provider Overview

Nine providers are supported. Eight are hosted APIs that need a key; one — Ollama — runs on your own hardware.

The LLM Provider dropdown

The list

ProviderAPI keyWhere to get it
OpenAIRequiredplatform.openai.com/api-keys
GeminiRequiredaistudio.google.com/apikey
AnthropicRequiredconsole.anthropic.com
OllamaOptionalSelf-hosted — an endpoint instead of a key
OpenRouterRequiredopenrouter.ai/keys
Mistral AIRequiredconsole.mistral.ai
CerebrasRequiredcloud.cerebras.ai
DeepSeekRequiredplatform.deepseek.com
CohereRequireddashboard.cohere.com/api-keys

Every provider except Ollama refuses to validate with an empty key.

Hosted or self-hosted

HostedOllama
CostPer token, billed by the providerYour hardware only
SetupPaste a keyInstall a server, pull a model
SpeedFast, no local resourcesDepends on your hardware
DataReview text leaves your serverStays on your infrastructure
QualityFrontier models availableLimited to open-weights models

Billing is between you and the provider

Webkul does not resell tokens or proxy traffic. The key you paste calls the provider directly from your Magento server.

Each provider needs its bridge package

A provider only works when its symfony/ai-*-platform package is installed. The module checks for all of them before reporting the packages as available, so install the whole set — see Install the AI Packages.

Next

  • How Validation Works
  • Choosing a Model
  • Switching Providers
  • Install Ollama
Next
How Validation Works