Skip to content

AI Provider Guides

Complete setup guides for all supported AI providers.

🆓 Free Tier Providers

Start with zero cost using these free-tier options:

Hugging Face

100,000+ open-source models

  • ✅ Free inference API
  • 🌍 Largest model collection
  • 🔓 Fully open source
  • 📊 Models by task: chat, classification, NER, summarization

Setup Guide →

Google AI Studio

Gemini models with generous free tier

  • ✅ 1,500 requests/day free
  • ⚡ Fast Gemini 2.0 Flash
  • 🎯 15 requests/minute
  • 💰 Pay-as-you-go option

Setup Guide →

🏢 Enterprise Providers

Production-grade providers for enterprise deployments:

Azure OpenAI

Enterprise AI with Microsoft Azure

  • 🔒 SOC2, HIPAA, ISO 27001 compliant
  • 🌍 Multi-region deployment (30+ regions)
  • 🛡️ Private endpoints with VNet
  • 💼 Enterprise SLAs

Setup Guide →

Google Vertex AI

Google Cloud ML platform

  • ☁️ GCP integration
  • 🔐 IAM, VPC, service accounts
  • 🌏 Global deployment
  • 🎯 Gemini, PaLM, Codey models

Setup Guide →

AWS Bedrock

Serverless AI on AWS

  • 📦 13 foundation models (Claude, Llama, Mistral)
  • 🔐 IAM, VPC integration
  • 🌍 Multi-region (us-east-1, eu-west-1, ap-southeast-1)
  • 💰 Pay-per-use pricing

Setup Guide →

🌍 Compliance-Focused

Providers with specific compliance certifications:

Mistral AI

European AI with GDPR compliance

  • 🇪🇺 EU data residency
  • ✅ GDPR compliant by default
  • 🔓 Open source models
  • 💰 Cost-effective

Setup Guide →

🔌 Aggregators & Proxies

Access multiple providers through unified interfaces:

OpenAI Compatible

OpenRouter, vLLM, LocalAI, and more

  • 🌐 100+ models through OpenRouter
  • 💻 Local deployment with vLLM
  • 🔓 Self-hosted with LocalAI
  • 🔄 Drop-in OpenAI replacement

Setup Guide →

LiteLLM

100+ providers through proxy

  • 🔄 Unified API for 100+ providers
  • 📊 Load balancing and fallbacks
  • 💰 Cost tracking
  • 🎯 Model routing

Setup Guide →

Quick Comparison

Provider Free Tier Enterprise GDPR Latency Best For
Hugging Face ✅ ❌ ✅ Medium Open source, experimentation
Google AI ✅ ✅ ✅ Low Free tier, Gemini
Mistral AI ❌ ✅ ✅ Low EU compliance, cost
OpenAI Compatible Varies ✅ Varies Varies Flexibility, local deployment
LiteLLM ❌ ✅ Varies Low Multi-provider, unified API
Azure OpenAI ❌ ✅ ✅ Low Enterprise, Microsoft ecosystem
Vertex AI ❌ ✅ ✅ Low Enterprise, GCP ecosystem
AWS Bedrock ❌ ✅ ✅ Low Enterprise, AWS ecosystem

Setup Strategies

```typescript const ai = new NeuroLink({ providers: [ { name: 'google-ai', priority: 1, config: { apiKey: process.env.GOOGLE_AI_KEY }, quotas: { daily: 1500 } }, { name: 'openai', priority: 2, config: { apiKey: process.env.OPENAI_API_KEY } } ], failoverConfig: { enabled: true, fallbackOnQuota: true } });

const result = await ai.generate({
  input: { text: "Hello world" }
});
```

```bash

Set up environment variables

export GOOGLE_AI_KEY="your-key" export OPENAI_API_KEY="your-key"

# Use with automatic failover
npx @juspay/neurolink generate "Hello world" \
  --provider google-ai
```

Strategy 2: Multi-Region Enterprise

const ai = new NeuroLink({
  providers: [
    {
      name: "azure-us",
      region: "us-east",
      config: {
        /* Azure US */
      },
    },
    {
      name: "azure-eu",
      region: "eu-west",
      config: {
        /* Azure EU */
      },
    },
    {
      name: "bedrock-us",
      region: "us-east",
      config: {
        /* Bedrock US */
      },
    },
  ],
  loadBalancing: "latency-based",
});

Strategy 3: GDPR Compliance

const ai = new NeuroLink({
  providers: [
    {
      name: "mistral",
      priority: 1,
      config: { apiKey: process.env.MISTRAL_API_KEY },
    },
    {
      name: "azure-eu",
      priority: 2,
      config: {
        /* Azure EU region */
      },
    },
  ],
  compliance: {
    framework: "GDPR",
    dataResidency: "EU",
  },
});

Next Steps

  1. Choose a provider based on your requirements (free tier, compliance, region)
  2. Follow the setup guide to get your API key
  3. Configure NeuroLink with the provider
  4. Test the integration with a simple request
  5. Add failover for production reliability