CommunicationGPT-3.5 Turbo

Email Classifier Using GPT-3.5 Turbo

Optimized prompts and cost breakdowns for running email classifier with GPT-3.5 Turbo.

About GPT-3.5 Turbo

Provider: openai
Context Window: 16K tokens
Input Cost: $0.5 / 1M tokens
Output Cost: $1.5 / 1M tokens

Best For

Legacy supportSimple classificationQuick responses

Optimized Prompts for GPT-3.5 Turbo

These prompts are tailored to work best with GPT-3.5 Turbo's capabilities

classify

Classify this email into one of these categories: {{categories}}

Also determine:
- Priority: High/Medium/Low
- Intent: Question/Complaint/Request/Information
- Sentiment: Positive/Neutral/Negative

Email:
{{email_content}}

Cost Breakdown

Estimated costs for running this workflow with GPT-3.5 Turbo

input tokens: ~1829 tokens
output tokens: ~623 tokens
cost per request: $0.0223
monthly 1000 requests: $34.00

Rate Limiting Considerations

Openai has rate limits of approximately 6132 RPM. Consider implementing request queuing for high-volume usage.

Monitoring with Administrate

Track GPT-3.5 Turbo API latency and error rates. Set up alerts for rate limit warnings and cost thresholds.