SUITE
GHOST/STUDIOACTIVE NODE

Setup

Ghost Studio needs one AI provider key to run the Planner → Developer → Reviewer pipeline. You only need one of the 12 below — when more than one is set, the app auto-selects by priority (Anthropic → Google → OpenAI → Groq → others). Connected providers are listed first on this page; the visible order is not the selection order.

0 of 12 configured. New providers can be added in lib/providers/registry.ts with a single entry; the rest of the app picks them up automatically.

No provider connected yet. Pick one below, then restart your dev server or redeploy so the new env var is picked up.

Available providers

Anthropic
Model: claude-sonnet-4-6
not set

Best overall architecture performance. $5 free credit on sign-up.

  1. Create a key at console.anthropic.com/settings/keys
  2. Set ANTHROPIC_API_KEY=<your-key> in .env.local (dev) or your host's env panel (Vercel / Fly / Railway).
  3. Restart the server so Next.js loads the new env var.
Google
Model: gemini-2.0-flash
not set

Generous free tier. Gemini 2.0 Flash by default.

  1. Create a key at aistudio.google.com/apikey
  2. Set GOOGLE_GENERATIVE_AI_API_KEY=<your-key> in .env.local (dev) or your host's env panel (Vercel / Fly / Railway).
  3. Restart the server so Next.js loads the new env var.
OpenAI
Model: gpt-4o
not set

Most broadly compatible. Pay-as-you-go from $5 minimum.

  1. Create a key at platform.openai.com/api-keys
  2. Set OPENAI_API_KEY=<your-key> in .env.local (dev) or your host's env panel (Vercel / Fly / Railway).
  3. Restart the server so Next.js loads the new env var.
Groq
Model: llama-3.3-70b-versatile
not set

Free tier, fastest inference. Llama 3.3 70B by default.

  1. Create a key at console.groq.com/keys
  2. Set GROQ_API_KEY=<your-key> in .env.local (dev) or your host's env panel (Vercel / Fly / Railway).
  3. Restart the server so Next.js loads the new env var.
DeepSeek
Model: deepseek-chat
not set

Cheapest frontier-class reasoning. DeepSeek V3 by default.

  1. Create a key at platform.deepseek.com/api_keys
  2. Set DEEPSEEK_API_KEY=<your-key> in .env.local (dev) or your host's env panel (Vercel / Fly / Railway).
  3. Restart the server so Next.js loads the new env var.
Mistral
Model: mistral-large-latest
not set

EU-hosted, GDPR-friendly. Mistral Large by default.

  1. Create a key at console.mistral.ai/api-keys
  2. Set MISTRAL_API_KEY=<your-key> in .env.local (dev) or your host's env panel (Vercel / Fly / Railway).
  3. Restart the server so Next.js loads the new env var.
Alibaba Model Studio (Qwen)
Model: qwen-plus
not set

Qwen 2.5 / 3 family. Free tier on sign-up.

  1. Create a key at modelstudio.console.alibabacloud.com
  2. Set DASHSCOPE_API_KEY=<your-key> in .env.local (dev) or your host's env panel (Vercel / Fly / Railway).
  3. Restart the server so Next.js loads the new env var.
xAI (Grok)
Model: grok-2-latest
not set

Grok 2 / 4 family with live web context.

  1. Create a key at console.x.ai
  2. Set XAI_API_KEY=<your-key> in .env.local (dev) or your host's env panel (Vercel / Fly / Railway).
  3. Restart the server so Next.js loads the new env var.
OpenRouter
Model: anthropic/claude-3.5-sonnet
not set

One key, 200+ models. Set OPENROUTER_MODEL to switch.

  1. Create a key at openrouter.ai/keys
  2. Set OPENROUTER_API_KEY=<your-key> in .env.local (dev) or your host's env panel (Vercel / Fly / Railway).
  3. Restart the server so Next.js loads the new env var.
Together AI
Model: meta-llama/Llama-3.3-70B-Instruct-Turbo
not set

Open-weights focused. Llama 3.3 70B by default.

  1. Create a key at api.together.xyz/settings/api-keys
  2. Set TOGETHER_API_KEY=<your-key> in .env.local (dev) or your host's env panel (Vercel / Fly / Railway).
  3. Restart the server so Next.js loads the new env var.
Fireworks
Model: accounts/fireworks/models/llama-v3p3-70b-instruct
not set

Fast OSS hosting. Llama 3.3 70B by default.

  1. Create a key at fireworks.ai/account/api-keys
  2. Set FIREWORKS_API_KEY=<your-key> in .env.local (dev) or your host's env panel (Vercel / Fly / Railway).
  3. Restart the server so Next.js loads the new env var.
Cerebras
Model: llama-3.3-70b
not set

Wafer-scale inference, ~2k tokens/sec. Llama 3.3 70B.

  1. Create a key at cloud.cerebras.ai
  2. Set CEREBRAS_API_KEY=<your-key> in .env.local (dev) or your host's env panel (Vercel / Fly / Railway).
  3. Restart the server so Next.js loads the new env var.

Bring Your Own Key

Enter your API keys below. They're stored only in your browser's localStorage and sent directly to the AI provider from the server.

Keys are never sent to our servers except when making AI requests. Your data stays between you and the AI provider.
Setup — Ghost Studio