Grabblist gives you an AI shopping assistant right inside your dashboard. But the AI brain behind it — the language model — is your choice. This guide covers every supported provider, how to get an API key, which model to pick, and how to set it up in under 2 minutes.

TL;DR: Go to Dashboard → Settings, pick your AI provider, paste your API key, save. Done.

1. Dashboard Agent vs MCP — Two Different AIs

Grabblist has two AI-powered features. They are independent and can use different models:

FeatureDashboard AgentMCP (Model Context Protocol)
WhereInside grabbitapp.com dashboardClaude Desktop or claude.ai
ModelYour choice (BYOK)Claude (Sonnet 4.5 by default)
API KeyRequired (your own)None (uses Claude account)
ToolsSearch, grab, collections, memory21 tools: browse, search, extract, grab, collections, items
SetupSettings → paste API keyOne-click MCP URL copy

This guide focuses on the Dashboard Agent since it requires API key configuration. For MCP setup, see our MCP Setup Guide.

2. Supported AI Providers

The dashboard agent supports two integration modes:

  • Anthropic (Native SDK) — Direct integration with Claude models. Best tool-use performance, native prompt caching.
  • OpenAI-Compatible API — Works with OpenAI, DeepSeek, Groq, Together AI, OpenRouter, Ollama, LM Studio, and any API that speaks the OpenAI chat completions format.

Provider Presets

ProviderBase URLRecommended ModelsPricing
Anthropic(native SDK)Claude Opus 4.5, Sonnet 4.5, Haiku 4.5$3–$15/M input, $15–$75/M output
OpenAIhttps://api.openai.com/v1GPT-4o, GPT-4o Mini$2.50–$5/M input
DeepSeekhttps://api.deepseek.com/v1DeepSeek V4 Pro, V4 Flash$0.27–$1.10/M input
Groqhttps://api.groq.com/openai/v1Llama 4 Maverick, DeepSeek R1 70BFree tier available
Together AIhttps://api.together.xyz/v1Llama 4 Maverick, DeepSeek R1$0.60–$3/M input
OpenRouterhttps://openrouter.ai/api/v1GPT-4o, Claude Sonnet 4.5, many othersVaries by model
CustomYour endpointAny OpenAI-compatible modelDepends on your setup

3. How to Get an API Key (Step by Step)

Anthropic (Claude)

  1. Go to console.anthropic.com
  2. Sign up or log in with your Google account
  3. Click API Keys in the left sidebar
  4. Click Create Key → give it a name like "Grabblist"
  5. Copy the key (starts with sk-ant-api03-...)
  6. Paste it into Grabblist Settings with the Anthropic preset selected
💡 Tip: New Anthropic accounts get $5 in free credits. Enough for hundreds of dashboard assistant queries with Haiku or dozens with Sonnet.

OpenAI (GPT-4o, GPT-4o Mini)

  1. Go to platform.openai.com/api-keys
  2. Sign up or log in
  3. Click Create new secret key
  4. Copy the key (starts with sk-proj-...)
  5. In Grabblist Settings, select OpenAI preset and paste
⚠️ Important: You need to pre-pay or add a billing method on OpenAI. Free credits expire after 3 months.

DeepSeek

  1. Go to platform.deepseek.com/api_keys
  2. Sign up (phone verification required in some regions)
  3. Click Create API Key
  4. Copy the key (starts with sk-...)
  5. In Grabblist Settings, select DeepSeek preset and paste

DeepSeek is the most cost-effective option. V4 Pro costs $1.10/M input tokens — roughly 5× cheaper than GPT-4o for comparable quality.

Groq (Fastest Inference)

  1. Go to console.groq.com/keys
  2. Sign up with Google or GitHub
  3. Click Create API Key
  4. Copy the key (starts with gsk_...)
  5. In Grabblist Settings, select Groq preset and paste
⚡ Speed: Groq runs on custom LPU hardware. Llama 4 Maverick on Groq responds in under 500ms — the fastest option for the dashboard assistant.

Together AI

  1. Go to api.together.xyz/settings/api-keys
  2. Sign up
  3. Copy your API key
  4. In Grabblist Settings, select Together AI preset and paste

OpenRouter (Multi-Provider Gateway)

  1. Go to openrouter.ai/keys
  2. Sign up
  3. Click Create Key
  4. Copy the key (starts with sk-or-v1-...)
  5. In Grabblist Settings, select OpenRouter preset and paste

OpenRouter is a gateway to 200+ models. You get one API key and can switch between OpenAI, Anthropic, Google, Meta, and others without creating separate accounts. Pricing is pay-per-token with no subscriptions.

Custom / Self-Hosted (Ollama, LM Studio, vLLM)

  1. Run your local LLM server (e.g., ollama serve)
  2. Note your endpoint URL (e.g., http://localhost:11434/v1)
  3. In Grabblist Settings, select Custom (OpenAI-compatible)
  4. Paste your endpoint URL in the Base URL field
  5. Enter any string as the API key (e.g., ollama) — local servers often ignore it
  6. Type your model name manually in the chat (e.g., llama3.1:8b)
🏠 Local LLM Requirements: Your model must support tool calling (function calling). Most recent models do — Llama 3.1+, Qwen 2.5+, Mistral, DeepSeek V3+. Tool calling quality varies: Claude and GPT-4o are the gold standard.

4. Setting Up in the Dashboard (2 Minutes)

  1. Open Settings. Go to Dashboard → Settings. Scroll to "Getting Started" → "Set up your API key."
  2. Choose your provider. Pick from the dropdown: Anthropic, OpenAI, DeepSeek, Groq, Together AI, OpenRouter, or Custom.
  3. Paste your API key. The placeholder text shows the expected format (e.g., sk-ant-api03-... for Anthropic).
  4. Set base URL (non-Anthropic only). The preset fills this automatically. Change it only if you use a proxy or custom endpoint.
  5. Click Save. A green checkmark confirms your key is connected.
  6. Start chatting. Open the AI assistant in the dashboard. Select your model from the dropdown (Claude Sonnet 4.5, GPT-4o, etc.) and start asking.
🔐 Security note: Your API key is encrypted in the database and only used server-side. It is never sent to the browser or exposed in client-side code. You can remove it anytime from Settings.

5. Choosing the Right Model

Once your API key is saved, the assistant shows a model dropdown. The list is fetched from your provider's API (for Anthropic and preset-matched providers) or shows sensible defaults.

By Task

TaskRecommended ModelWhy
Quick product lookupsClaude Haiku 4.5 / GPT-4o Mini / DeepSeek V4 FlashFast, cheap, sufficient for simple queries
Multi-step shopping researchClaude Sonnet 4.5 / GPT-4oBest tool-use ability, follows complex instructions
Cross-store price comparisonClaude Sonnet 4.5 / DeepSeek V4 ProHandles large context windows, multiple search results
Product description writingClaude Opus 4.5 / GPT-4oBest prose quality for collection notes
Fastest responseGroq Llama 4 MaverickSub-500ms token generation on custom LPU hardware
Budget-consciousDeepSeek V4 Flash / GPT-4o Mini$0.27–$0.60/M input, excellent value

6. MCP: Which Model Does It Use?

MCP (Model Context Protocol) connects Claude to Grabblist's tools. The model is determined by your Claude client:

  • claude.ai (web): Claude Sonnet 4.5 by default. Pro users can switch to Opus 4.5 or Haiku 4.5 via the model picker.
  • Claude Desktop: Uses the model selected in the app. Go to Claude → Settings → Model to change it.
  • Claude Code (CLI): Uses the model specified with --model flag or the default Sonnet 4.5.

MCP does not require an API key — it uses your Claude account's built-in quota. If you have Claude Pro ($20/month), you get 5× more messages with MCP tools. See the MCP Setup Guide for the full walkthrough.

7. Troubleshooting

ErrorLikely CauseFix
"Invalid API key"Key is wrong or expiredRegenerate key on your provider's console and re-paste
"Insufficient credits"Provider balance depletedAdd funds on your provider's billing page
"Model not available"Your API key lacks access to that modelCheck provider model availability; try a different model from the dropdown
"Rate limit exceeded"Too many requests in a short periodWait 30 seconds; upgrade your provider tier for higher limits
"Connection refused" (custom endpoint)Local server not running or wrong URLVerify ollama serve is running; check firewall; test with curl
Assistant doesn't use toolsModel lacks tool-calling supportSwitch to a model with native function calling (Claude, GPT-4o, Llama 3.1+)
Blank model listProvider API unreachable or key invalidCheck your internet; verify the base URL is correct; try a different preset

8. Frequently Asked Questions

Do I need to pay for the AI models?

Grabblist does not charge for AI usage. You bring your own API key from your chosen provider. Most providers offer free credits for new accounts (OpenAI: $5, Anthropic: $5, DeepSeek: $2, Groq: free tier). After that, you pay the provider directly. MCP usage through ChatGPT or Claude uses the AI account you connect it from.

Which model should I pick?

For the dashboard assistant: Claude Sonnet 4.5 or GPT-4o for complex shopping research, Claude Haiku 4.5 or GPT-4o Mini for quick lookups. DeepSeek V4 Pro if you prefer the DeepSeek ecosystem. Groq Llama 4 Maverick for the fastest responses. For MCP: Claude Sonnet 4.5 is the default and recommended — it handles multi-step shopping workflows best.

Can I use a local LLM like Ollama or LM Studio?

Yes. Select "Custom (OpenAI-compatible)" in Settings and enter your local endpoint (e.g., http://localhost:11434/v1 for Ollama). Make sure your local model supports tool calling (function calling) — most modern models do.

Is my API key stored securely?

Yes. Your API key is encrypted at rest in Supabase and never exposed to the browser. It is only used server-side to forward requests to your chosen AI provider. You can remove it at any time from Settings.

Can I switch providers later?

Absolutely. Change your provider preset in Settings, paste the new API key, and hit Save. The assistant will use your new provider immediately. Your chat history stays intact.

What is MCP and how is it different from the dashboard agent?

MCP (Model Context Protocol) connects ChatGPT, Claude Desktop, or claude.ai directly to Grabblist's 21 shopping tools — web search, product extraction, price comparison, and more. The dashboard agent is the AI assistant inside the Grabblist web app. MCP uses the model selected in the AI client you connect.


Ready to set up? Go to Settings →

Need the MCP setup instead? MCP Setup Guide →