LLM Providers

VibeReady supports multiple LLM providers out of the box, allowing you to add AI-powered features to your application with a single API key configuration.

---

Supported Providers

Provider	Get API Key	Best For
OpenRouter	openrouter.ai/keys	100+ models, $1 free credit
OpenAI	platform.openai.com	GPT-4, GPT-3.5
Anthropic	console.anthropic.com	Claude models
Google	aistudio.google.com	Gemini models

---

Setup

1. Add to Local Environment

Set the provider and API key in your .env.local file:

LLM_PROVIDER="openrouter"  # or: openai, anthropic, google
LLM_API_KEY="your-api-key"

2. Add to CI/CD

Add the provider and key to your CI/CD pipeline (e.g., GitHub Secrets) so they are available during builds and deployments.

3. Add to Terraform (GCP Deployment)

For GCP deployments, add the API key to your Terraform configuration file and apply the changes:

terraform apply

This creates the secret in GCP Secret Manager, which Cloud Run accesses at runtime.

4. Restart Dev Server

make dev

---

Provider Endpoints

Each provider uses a different API endpoint. VibeReady handles routing automatically based on the LLM_PROVIDER value.

Provider	Base URL
OpenRouter	https://openrouter.ai/api/v1
OpenAI	https://api.openai.com/v1
Anthropic	https://api.anthropic.com/v1
Google	https://generativelanguage.googleapis.com/v1

---

Recommendation

Start with OpenRouter. It provides access to 100+ models (including OpenAI, Anthropic, and Google models) through a single API key. You can switch between models without changing any application code, and it includes $1 of free credit to get started.

---

Troubleshooting

Issue	Fix
”Invalid API key”	Check key format and restart the dev server.
”Model not available”	Try a different model or check the provider’s status page.
”Rate limit exceeded”	Add delay between requests or upgrade your plan.

---

Related Docs

• MCP Tools — AI-assisted development with Context7 and Chrome DevTools
• GCP Deployment — deploy with LLM keys in Secret Manager