Groq Multi Env Setup

Groq Multi-Environment Setup

Overview

Configure Groq API access across development, staging, and production with the right model, rate limit strategy, and secret management per environment. Key insight: use llama-3.1-8b-instant in development (cheapest, fastest), match production model in staging, and harden production with retries and fallbacks.

Prerequisites

• A Groq account with API keys from console.groq.com/keys — ideally a separate key (or organization) per environment.
• Node project with the groq-sdk package installed (npm install groq-sdk).
• NODE_ENV set per environment (development / staging / production).
• A secret store for staging/production keys: GitHub Actions secrets, AWS Secrets Manager, GCP Secret Manager, or HashiCorp Vault.

Environment Strategy

Instructions

The full, copy-paste implementation lives in the reference files — this section is the map. Read the implementation walkthrough for the code module, service wrapper, and verify script, and secrets & deployment for per-platform key management, Docker Compose profiles, and rate-limit inspection.

1. Build the config module (config/groq.ts). One configs record keyed by environment resolves model, token budget, retries, timeout, and logging, then validates that a key is present with an environment-specific error message. The essential skeleton:

   const configs: Record<string, GroqEnvConfig> = {
     development: { model: "llama-3.1-8b-instant", maxRetries: 1, logRequests: true, /* ... */ },
     staging:     { model: "llama-3.3-70b-versatile", maxRetries: 3, logRequests: false, /* ... */ },
     production:  { model: "llama-3.3-70b-versatile", maxRetries: 5, logRequests: false, /* ... */ },
   };
   export function getGroqConfig(): GroqEnvConfig {
     return configs[process.env.NODE_ENV || "development"] || configs.development;
   }
   

   See implementation.md § Step 1 for the full module including key validation and the memoized getGroqClient().

2. Wire an environment-aware service (services/groq-service.ts) that reads the resolved config, logs only when logRequests is on, and surfaces the retry-after header on 429. Full code in implementation.md § Step 2.

3. Source secrets per platform. Dev reads a git-ignored .env.local; staging uses CI/CD secrets; production pulls from a secret manager. Commands for GitHub Actions, AWS, GCP, and Vault are in secrets-and-deployment.md § Step 3.

4. Deploy with Docker Compose profiles so each environment injects its own key (env var for dev/staging, external Docker secret for prod). See secrets-and-deployment.md § Step 4.

5. Verify each environment with scripts/verify-groq-env.ts, which prints the resolved model/retries and does a live round-trip. Full script in implementation.md § Step 5.

6. Inspect rate limits per key via the x-ratelimit-* response headers — see secrets-and-deployment.md § Step 6.

Output

After setup, each environment resolves its own Groq configuration and the verify script confirms a live connection. Expected output from verify-groq-env.ts in production:

Environment: production
Model: llama-3.3-70b-versatile
Max retries: 5
API key prefix: gsk_AbCd...
Connection: OK (312ms)
Model response: OK

You end with: a config/groq.ts that selects model/retries/logging by NODE_ENV, a service wrapper that logs verbosely only in dev, per-environment keys sourced from the right secret store, and Docker Compose profiles that never leak a production key into the process environment.

Error Handling

Examples

Resolve the config for the current environment:

import { getGroqConfig } from "./config/groq";

const config = getGroqConfig();      // picks dev/staging/prod by NODE_ENV
console.log(config.model);           // "llama-3.1-8b-instant" in dev

Complete a chat with the environment default model:

import { complete } from "./services/groq-service";

const answer = await complete([{ role: "user", content: "Summarize in one line." }]);

Verify production before a deploy:

NODE_ENV=production GROQ_API_KEY_PROD=gsk_... npx tsx scripts/verify-groq-env.ts

Full, runnable versions of every snippet are in implementation.md and secrets-and-deployment.md.

Resources

• Groq Console
• Groq API Keys
• Groq Rate Limits
• Groq Spend Limits
• Implementation walkthrough — config module, service, verify script
• Secrets & deployment — secret managers, Docker Compose, rate limits

Next Steps

For deployment configuration, see the groq-deploy-integration skill, which builds on this environment strategy to wire CI/CD deploy pipelines and health checks.