API Keys & Model Providers
Reliant supports multiple AI model providers, allowing you to choose the best models for your workflow. You can configure API keys through environment variables, configuration files, or the Settings UI.
Quick Start
Using an Existing Claude Code Subscription
If you already have a Claude Code subscription, you can use it with Reliant:
Get your API key by running this command in your terminal:
claude setup-tokenFollow the authentication flow that opens in your browser
Copy the API key shown after authentication
Configure Reliant using one of these methods:
Option A: Settings UI
- Open Reliant Settings
- Navigate to AI Providers
- Select “Anthropic” provider
- Paste your API key
- Click “Save” or “Test Connection”
Option B: Environment Variable
export ANTHROPIC_API_KEY="your-api-key-here"Option C: Configuration File (
.reliant.json){ "providers": { "anthropic": { "apiKey": "your-api-key-here" } } }
Supported Providers
Reliant supports the following AI model providers:
Anthropic (Claude)
Available Models: Claude 4.5 Sonnet, Claude 4.5 Opus, Claude 4.5 Haiku
Configuration:
export ANTHROPIC_API_KEY="sk-ant-..."Or in .reliant.json:
{
"providers": {
"anthropic": {
"apiKey": "sk-ant-...",
"disabled": false
}
}
}Getting an API Key:
- Sign up at console.anthropic.com
- Or use existing Claude Code subscription (see Quick Start above)
OpenAI
Available Models: GPT-5.2, GPT-5 Mini, GPT-5.2 Pro, GPT-5.2 Codex
Configuration:
export OPENAI_API_KEY="sk-..."Or in .reliant.json:
{
"providers": {
"openai": {
"apiKey": "sk-...",
"disabled": false
}
}
}Getting an API Key:
- Sign up at platform.openai.com
- Navigate to API Keys section
- Create new secret key
Google Gemini
Available Models: Gemini 3 Pro, Gemini 3 Flash, Gemini 2.5 Pro, Gemini 2.5 Flash
Configuration:
export GEMINI_API_KEY="..."Or in .reliant.json:
{
"providers": {
"gemini": {
"apiKey": "...",
"disabled": false
}
}
}Getting an API Key:
- Visit ai.google.dev
- Sign in with Google account
- Create API key in API Keys section
OpenRouter
Configuration:
export OPENROUTER_API_KEY="sk-or-..."Or in .reliant.json:
{
"providers": {
"openrouter": {
"apiKey": "sk-or-...",
"disabled": false
}
}
}Note on Model Support: OpenRouter can be used to access the Anthropic, OpenAI, and Google models listed above. Other custom models available on OpenRouter are not currently supported in Reliant.
Getting an API Key:
- Sign up at openrouter.ai
- Navigate to Keys section
- Create new API key
Configuration Priority
Reliant checks for configuration in this order:
- Environment Variables (highest priority)
- Configuration File (
.reliant.json) - Settings UI (stored in config file)
Environment variables override configuration file settings, allowing temporary changes without modifying files.
Testing API Keys
After configuring a provider:
- Open Reliant Settings
- Navigate to the AI Providers section
- Find your configured provider
- Click “Test Connection” or “Validate”
- Verify you see a success message
Common Issues
“Invalid API Key” Error
Solutions:
- Verify key is copied correctly with no extra spaces
- Check key hasn’t expired (regenerate if needed)
- Ensure you’re using the correct provider (e.g., Anthropic key for Claude models)
- For Claude Code keys, verify they’re still active
“Rate Limit Exceeded”
Solutions:
- Wait before sending more requests
- Check your provider’s rate limits for your tier
- Consider upgrading your plan
- Use a different API key or provider temporarily
Provider Not Showing in UI
Solutions:
- Restart Reliant after configuration changes
- Check configuration file syntax (JSON must be valid)
- Ensure provider isn’t marked as
"disabled": true
Connection Timeout
Solutions:
- Verify internet connection
- Check firewall settings
- For local models, ensure server is running
- Disable VPN temporarily to test
Security Best Practices
Never Commit API Keys
Add to .gitignore:
.reliant.json
.envUse Environment Variables for CI/CD
In CI/CD pipelines, set API keys as secret environment variables:
env:
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}Rotate Keys Regularly
- Rotate API keys every 90 days
- Immediately rotate if a key may have been exposed
- Use different keys for development and production
Limit Key Permissions
Where possible:
- Use read-only or limited-scope keys
- Create separate keys for different projects
- Monitor key usage in provider dashboards
Rate Limits and Billing
Different provider tiers have different limits. Please refer to your provider’s documentation for the most up-to-date information on rate limits and pricing:
- Anthropic: Rate Limits | Pricing
- OpenAI: Rate Limits | Pricing
- Google Gemini: Pricing and Limits
- OpenRouter: Models and Pricing
Related Topics
- Presets - Configure which models workflows use
- MCP Servers - Extend capabilities with external tools
- Troubleshooting - Solve common API key issues