Skip to content

AI Provider Configuration

Updated

On this page36

Overview#

AutomateNexus CRM includes AI-powered features such as smart replies and message summaries in chat, AI agents, AI voice calling and SMS, email generation and composition, send-time optimization, insights and analytics, document processing, contract analysis and proposal scoring. They run on an AI provider of your choice, connected with your own API key, or on AI credits from AutomateNexus CRM ($5 a month per 5 million tokens) when you have not added one. No plan includes AI usage: with neither a key nor credits, these features are off. AutomateNexus CRM supports many providers, including OpenAI, Anthropic Claude, Google Gemini, Mistral AI, Groq, DeepSeek, z.ai (GLM), Cohere, AI21 Labs, Together AI, Replicate, Straico, OpenRouter, DeepInfra and Fireworks AI, as well as servers you run yourself (Ollama, LM Studio, vLLM or any OpenAI-compatible API). You can configure several providers at once, mark one as primary, and choose which features each provider serves, with a different model per feature if you like. This guide walks through the setup and explains model selection.

Prerequisites#

Before configuring AI providers, ensure you have:

  • An active AutomateNexus CRM account with permission to change your organization's settings.
  • An account with at least one supported AI provider.
  • A valid API key from your chosen provider with sufficient credits or an active billing plan.
  • An understanding of the AI features you plan to use (this affects which models you should select).
  1. Log in to your AutomateNexus CRM dashboard.
  2. In the sidebar, under Administration, click Integrations.
  3. Choose Automation in the left menu of the Integrations page.
  4. Scroll to the AI providers heading.

The AI providers section shows an AI credits card (what your organization has used this month), an Ollama on my computer card, your Active Providers with their default model and a Primary badge on the primary one, and a Select a provider to configure… dropdown listing every provider you have not connected yet. Above it, the Lead enrichment heading holds a separate choice of model for enriching new leads.

Connecting a Provider#

The steps are the same for every hosted provider:

  1. Under AI providers, pick the provider from the Select a provider to configure… dropdown. To change one you have already connected, expand it under Active Providers and click Configure.
  2. In the Configure dialog, leave the API Key Name as suggested (for example OPENAI_API_KEY) and paste your key into API Key. Keys are stored securely and are not shown again.
  3. Choose a Default model. The dialog suggests a few models for the provider; where it offers Load models from the provider, enter your key first and the full list from your account replaces the suggestions (OpenRouter's catalog loads on its own, with prices per million tokens). The default model is used for every feature unless you override it below.
  4. Switch on Set as primary provider if this provider should be the organization default. The first provider you add is primary automatically.
  5. Under Enabled Features, tick the features this provider should serve. Beside each enabled feature you can pick a model for just that feature, or leave Use default.
  6. Click Save. The provider appears under Active Providers; expand it to see its features and per-feature models, or click Remove to disconnect it.

Anthropic (Claude) Setup#

About Anthropic#

Anthropic offers the Claude family of models, known for their strong reasoning capabilities, safety features, and ability to handle long documents. Claude models are excellent for email composition, document analysis, and complex conversational tasks.

Getting Your Anthropic API Key#

  1. Go to console.anthropic.com and sign in or create an account.
  2. Navigate to API Keys in the left sidebar.
  3. Click Create Key.
  4. Give the key a descriptive name (e.g., "AutomateNexus CRM").
  5. Copy the API key. It will start with sk-ant-.
  6. Ensure you have added a payment method and set a usage limit under Plans & Billing in the Anthropic console.

Then connect it as described under Connecting a Provider, choosing Anthropic Claude in the provider dropdown.

OpenAI (GPT) Setup#

About OpenAI#

OpenAI provides the GPT family of models, widely adopted and well-suited for general-purpose text generation, summarization, and classification tasks within AutomateNexus CRM.

Getting Your OpenAI API Key#

  1. Go to platform.openai.com and sign in.
  2. Navigate to API Keys in the sidebar (under your profile settings).
  3. Click Create new secret key.
  4. Name the key (e.g., "AutomateNexus CRM") and set permissions to All or restrict to specific capabilities.
  5. Copy the key. It will start with sk-.
  6. Ensure billing is set up in your OpenAI account.

Then connect it as described under Connecting a Provider, choosing OpenAI in the provider dropdown.

Google (Gemini) Setup#

About Google Gemini#

Google offers the Gemini family of models through Google AI Studio or Vertex AI. Gemini models support multimodal inputs and are well-integrated with the Google ecosystem.

Getting Your Google AI API Key#

  1. Go to aistudio.google.com and sign in with your Google account.
  2. Click Get API Key in the top navigation.
  3. Click Create API Key and select a Google Cloud project (or create a new one).
  4. Copy the generated API key.

Then connect it as described under Connecting a Provider, choosing Google Gemini in the provider dropdown.

Mistral Setup#

About Mistral#

Mistral AI offers high-performance open-weight models that are efficient and cost-effective. They are a strong choice for organizations that value the flexibility of open models or need European data processing.

Getting Your Mistral API Key#

  1. Go to console.mistral.ai and sign in or create an account.
  2. Navigate to API Keys.
  3. Click Create new key.
  4. Name the key and copy it.
  5. Ensure billing is configured in your Mistral account.

Then connect it as described under Connecting a Provider, choosing Mistral AI in the provider dropdown.

Groq Setup#

About Groq#

Groq provides ultra-fast inference through custom hardware (LPU). It hosts popular open-source models such as Llama 3.3 70B, Mixtral 8x7B and Gemma 2 9B and delivers responses with very low latency, which suits features where speed matters most, such as the phone receptionist and live chat.

Getting Your Groq API Key#

  1. Go to console.groq.com and sign in or create an account.
  2. Navigate to API Keys.
  3. Click Create API Key.
  4. Name the key and copy it.

Then connect it as described under Connecting a Provider, choosing Groq in the provider dropdown.

Other Hosted Providers#

DeepSeek, z.ai (GLM), Cohere, AI21 Labs, Together AI, Replicate, Straico, OpenRouter, DeepInfra and Fireworks AI connect the same way, with an API key from the provider's own console. OpenRouter is one key for hundreds of open and closed models with per-token pricing; DeepInfra and Fireworks AI host open-weight models such as Qwen3, DeepSeek V3 and Llama.

Self-Hosted and Local Models#

Your Own Server#

Choose Ollama (self-hosted), LM Studio (self-hosted), vLLM / OpenAI-compatible server or Custom OpenAI-compatible API from the provider dropdown. Instead of a key, the dialog asks for:

  • Server URL — A URL reachable from the internet, because the app runs in the cloud. The dialog suggests a free Cloudflare Tunnel (cloudflared tunnel --url http://localhost:11434 for Ollama; port 1234 for LM Studio; port 8000 for vLLM), and Ollama must be started with OLLAMA_HOST=0.0.0.0. The /v1 suffix is added for you if it is missing.
  • API key — Optional; only if your server or tunnel requires a bearer token.
  • Default model — The model name your server exposes (for Ollama, the name you pulled). Recommended models are offered as chips, or load the list once the server URL is reachable.

Nothing is billed per token; the server runs on your hardware.

Ollama on My Computer#

The Ollama on my computer card runs open models on the machine you are using, with nothing to expose and nothing billed per token. It works while a tab of the app is open on that machine.

Model Selection and Feature Assignment#

Setting a Primary Provider#

The provider with Set as primary provider switched on is the organization default: an AI agent whose model is Organization default uses its default model, and the website Messenger and the phone receptionist use it unless told otherwise. Switch it on in another provider's Configure dialog to move the primary.

Per-Feature Model Assignment#

Each provider's Enabled Features list is grouped as follows, and every enabled feature can have its own model:

  • Chat & Messaging — Smart Replies, Message Summary, AI Message Assistant
  • AI Agents — Agent Orchestrator (Karrie), Sales Agent, Support Agent, Operations Agent, Analytics Agent, Scheduler Agent
  • Communications — AI Voice Calling, AI SMS, Email Generation, AI Email Compose, Send Time Optimization
  • Content & Analytics — Insights & Analytics, Document Processing, Contract Analysis, Proposal Scoring

Use Select all or None to change the whole list at once; the dialog counts how many features are enabled, and model pickers appear only for enabled features.

Cost Optimization Tips#

  • Use smaller, faster models for high-volume, repetitive features and reserve larger models for work that needs nuance.
  • Monitor usage under AI → AI Usage: input, output and total tokens with an estimated cost, broken down by provider, by model and by agent or feature.
  • Give each AI agent a Monthly budget in its Limits section; the agent pauses itself when it reaches it.
  • The AI credits card shows the tokens your organization has used this month on AutomateNexus CRM's model. Credits come in blocks of 5 million tokens at $5 a month, added by an admin under Settings → Plans, and an agency shares them with the client organizations on its plan. Calls on your own provider key never use credits.

Lead Enrichment#

The Lead enrichment heading, above AI providers, sets the model used to enrich new leads on its own: choose a Provider (OpenAI, Anthropic (Claude) or Groq, which has a free tier), a Model, and enter that provider's key.

Agent Model Settings#

Response controls live on each agent rather than on the provider. In AI → AI Agents, an agent's Model section has the model choice, a Response length in tokens and a Creativity setting, and its Instructions section holds the standing brief that shapes its output.

Testing AI Features#

  1. Test the key: in the Configure dialog, where Load models from the provider is offered, a list of models means the key works.
  2. Test an agent: open an agent under AI → AI Agents and start a run by hand from its page.
  3. Test the Messenger: with Answer with AI on under Inbox → Support Hub → Messenger, ask a question in the chat on your website.
  4. Test meeting notes: open a recorded meeting under Scheduling → AI Notetaker and ask a question on its Ask tab.

Troubleshooting#

API Key Rejected#

  • Verify the API key is correct and complete (no trailing spaces or missing characters).
  • Check that your AI provider account is active and has billing configured.
  • Ensure the API key has not been revoked or expired.
  • For OpenAI, verify your organization has not exceeded its usage quota.

Slow AI Responses#

  • Switch the feature or agent to a faster model, or to a Groq-hosted model.
  • Shorten an agent's Response length.
  • Check the AI provider status page for any ongoing service issues.
  • Ensure your internet connection is stable.

AI Output Quality Issues#

  • Tighten an agent's Instructions, or the Messenger's Guidance, to give better context.
  • Try a larger model for that feature with the per-feature model picker. Larger models generally produce higher quality output but at higher cost and latency.
  • Provide more context in the records the AI works from (detailed notes, conversation history).

Usage Costs Higher Than Expected#

  • Review AI → AI Usage to see which provider, model and agent consume the most tokens.
  • Move high-volume features to smaller, cheaper models.
  • Set agent monthly budgets, or turn on credit metering.
  • Untick features a provider does not need to serve.

Was this page helpful?