Back to Churn Predictor
Customer SuccessLlama 3 (70B)
Churn Predictor Using Llama 3 (70B)
Optimized prompts and cost breakdowns for running churn predictor with Llama 3 (70B).
About Llama 3 (70B)
- Provider
- meta
- Context Window
- 8K tokens
- Input Cost
- $0.9 / 1M tokens
- Output Cost
- $0.9 / 1M tokens
Best For
Self-hostingOpen sourcePrivacy
Optimized Prompts for Llama 3 (70B)
These prompts are tailored to work best with Llama 3 (70B)'s capabilities
analyze
Analyze this customer's churn risk:
{{customer_data}}
Usage trends: {{usage_trends}}
Support tickets: {{support_history}}
Provide:
1. Churn risk score (1-100)
2. Key risk factors
3. Recommended interventions
4. Urgency levelCost Breakdown
Estimated costs for running this workflow with Llama 3 (70B)
- input tokens
- ~1676 tokens
- output tokens
- ~211 tokens
- cost per request
- $0.0284
- monthly 1000 requests
- $2.64
Rate Limiting Considerations
Check provider rate limits for Llama 3 (70B) Monitor 429 errors in Administrate
Monitoring with Administrate
Track latency and token usage for Llama 3 (70B) in Administrate dashboard