Skip to main content
AI Translations for Laravel supports three major LLM providers. You can configure which provider to use and customize the models for different use cases.

​
Selecting a provider

Set the active provider in your config/ai-translations.php file: 
'provider' => 'anthropic', // Options: 'openai', 'anthropic', 'gemini'
Or use the environment variable in your .env file: 
AI_TRANSLATIONS_PROVIDER=anthropic
The default provider is Gemini, which offers a good balance of speed, quality, and cost.

​
Provider configuration

​
OpenAI setup

OpenAI provides high-quality translations with models like GPT-4 and GPT-5.

​
Environment variables

Add these variables to your .env file:
.env
OPENAI_API_KEY=sk-proj-...

​
Configuration

Configure OpenAI in config/ai-translations.php:
'provider' => 'openai',
'openai' => [
    'model' => 'gpt-5-mini',
    'fast_model' => 'gpt-5-nano',
    'api_key' => env('OPENAI_API_KEY'),
],

​
Available models

​
openai.model
string
default:"gpt-5-mini"
The primary model used for standard translations. Recommended options:
  • gpt-5-mini - Latest efficient model (default)
  • gpt-4o - Previous generation flagship model
  • gpt-4-turbo - Faster GPT-4 variant
​
openai.fast_model
string
default:"gpt-5-nano"
The model used when running with the --fast flag. Optimized for speed and cost:
  • gpt-5-nano - Ultra-fast model (default)
  • gpt-4o-mini - Compact but capable
​
openai.api_key
string
required
Your OpenAI API key. Get one from platform.openai.com.

​
Getting an API key

  1. Sign up at platform.openai.com
  2. Navigate to API keys section
  3. Create a new secret key
  4. Add the key to your .env file
Keep your API key secure. Never commit it to version control.

​
Fast mode

When you run the translate command with the --fast flag, the package automatically switches to the configured fast_model: 
php artisan translate --fast
Fast models are:
  • More cost-effective
  • Faster to respond
  • Slightly less precise for complex translations
Use fast mode for large translation jobs or when iterating quickly. Use standard models for production translations where quality is critical.

​
Model selection best practices

​
For production translations

  • OpenAI: gpt-5-mini or gpt-4o
  • Anthropic: claude-sonnet-4-5 or claude-opus-4
  • Gemini: gemini-flash-latest or gemini-pro-latest

​
For development or large batches

  • OpenAI: gpt-5-nano or gpt-4o-mini
  • Anthropic: claude-haiku-4-5
  • Gemini: gemini-flash-lite-latest

​
Troubleshooting

​
Invalid API key error

If you receive an authentication error:
  1. Verify your API key is correctly set in .env
  2. Ensure there are no extra spaces or quotes around the key
  3. Check that you’ve cleared the config cache: php artisan config:clear
  4. Verify your API key is active in the provider’s console

​
Provider not found

If you see a “Invalid provider” error:
  1. Verify the provider setting in config/ai-translations.php
  2. Ensure it’s one of: openai, anthropic, or gemini
  3. Clear the config cache: php artisan config:clear

​
Next steps

Configure languages

Set up which languages to translate

Build docs developers (and LLMs) love

Get started for freeTalk to us