Integrates any AI model from the < OpenRouter.ai > library directly into your HubSpot workflows, enabling AI-powered content generation, analysis, and decision-making. When you need AI assistance for content creation, data analysis, lead scoring, email personalization, or any task that benefits from advanced language models like GPT-4, Claude, or specialized AI models.
Automates complex reasoning tasks, generates personalized content at scale, provides intelligent insights, and enables sophisticated AI-driven workflows without requiring separate AI integrations.
Add the "OpenRouter AI" action to your workflow
Select an AI model from the available options
Write your prompt with any HubSpot property tokens
Test with a few records to validate responses
- Dynamic Dropdown (populated from OpenRouter.ai )
- The specific AI model to use for processing your prompt
-
gpt-5, claude-4.5-sonnet, llama-2-70b-chat - Options include GPT models, Claude, Llama, and many specialized models
- Text Area
- The instruction or question you want the AI to process
-
Write a personalized follow-up email for {{contact.firstname}} who downloaded our {{recent_content_title}} guide - Can include HubSpot property tokens and complex instructions
- Dynamic Dropdown (populated based on selected model)
- Specific AI provider to use when multiple providers offer the same model
-
Default (automatically balances across providers) -
OpenAI, Anthropic, Together AI - Useful for consistency or when you prefer specific providers
- Boolean Checkbox
- Enables the AI to search the web for current information before responding
-
false - Additional $0.10 USD per request
-
true for current events, market data, or recent information - Provides more accurate and up-to-date responses
- Text
- The AI's response in plain text format
- Store in HubSpot properties, use in subsequent workflow actions
- Raw text response from the AI model
- Text (HTML formatted)
- The AI's response formatted as HTML (useful for rich content)
- Email templates, rich text properties, web content
- Formatted response with headings, lists, and styling
- Text
- Source citations when web search is enabled
- Track information sources, validate AI responses
-
wikipedia.org, company-website.com or "No citations"
Generate custom follow-up emails based on contact behavior and properties
- Model:
gpt-4 - Prompt:
Write a personalized follow-up email for {{contact.firstname}} who works at {{company.name}} in the {{contact.industry}} industry. They recently {{recent_activity}}. Keep it professional and under 150 words. - Web Search:
false
Personalized emails for each contact based on their specific context
Use AI to analyze lead quality based on multiple data points
- Model:
claude-3-sonnet - Prompt:
Analyze this lead: Company: {{company.name}}, Industry: {{company.industry}}, Size: {{company.numberofemployees}}, Recent Activity: {{recent_page_views}}. Provide a lead score from 1-10 and explain why. - Web Search:
false
AI-generated lead scores with reasoning for sales team prioritization
Summarize long-form content or meeting notes for quick review
- Model:
gpt-4 - Prompt:
Summarize the following meeting notes in 3 bullet points: {{meeting.notes}} - Web Search:
false
Concise summaries for easy consumption and follow-up
Get current market insights for deals in specific industries
- Model:
gpt-4 - Prompt:
What are the current market trends and challenges in the {{company.industry}} industry that might affect a {{deal.dealtype}} deal worth {{deal.amount}}? - Web Search:
true
Current market context to inform sales strategies
Choose models based on your specific needs:
- Best for complex reasoning, creative tasks, and general intelligence
- Excellent for analysis, writing, and following detailed instructions
- Cost-effective for simpler tasks and high-volume processing
- Task-specific models for coding, math, or domain expertise
- Clear, detailed instructions produce better results
- Show the AI what you want with examples
- Specify length, format, tone, and style requirements
- Provide relevant background information
- Refine prompts based on actual results
- Different models have different pricing (check OpenRouter.ai )
- Adds $0.10 per request but provides current information
- Longer prompts and responses cost more
- Some providers may be more cost-effective
- Requests timeout after 60 seconds if the AI model doesn't respond
- Failed requests are automatically retried once before failing the workflow
- < OpenRouter.ai > handles rate limiting - workflows will wait and retry if limits are hit
- Each model has maximum token limits for input + output combined
- Large responses are streamed back to prevent timeouts
- API errors from < OpenRouter.ai > are passed through to help with debugging
Your prompt is processed with HubSpot property values
Selected model processes your prompt (with web search if enabled)
AI response converted to both text and HTML formats
Results available for use in subsequent workflow actions
Workflow fails immediately with account error Ensure your < OpenRouter.ai > API key is properly configured in app settings Responses don't match expectations or vary widely Refine your prompt with more specific instructions and examples
AI responses end abruptly or seem truncated
- The model may have hit its token limit - try a model with higher limits or shorter prompts
- Some models have built-in response length limits - specify desired length in your prompt
- Check if the response is actually complete but formatted unexpectedly
- HubSpot properties also have a character limit that you may be hitting
Unexpected charges from < OpenRouter.ai > Monitor usage, choose cost-effective models, and avoid web search when not needed