OpenAI
Configure MyDeskBot to use OpenAI models.
Overview
OpenAI provides some of the most capable AI models, including GPT-4 and GPT-3.5 Turbo.
Supported Models
- GPT-4o - Most capable model, multimodal
- GPT-4 Turbo - High performance, cost-effective
- GPT-4 - Advanced reasoning
- GPT-3.5 Turbo - Fast, cost-effective
Get API Key
- Visit platform.openai.com
- Sign up or log in
- Go to API Keys section
- Create a new API key
- Copy the key (you'll only see it once!)
Configuration Options
Model Selection
Choose the model that fits your needs:
| Model | Best For | Cost | Speed |
|---|---|---|---|
| GPT-4o | Complex tasks, multimodal | High | Medium |
| GPT-4 Turbo | Most tasks | Medium | Fast |
| GPT-4 | Advanced reasoning | High | Slow |
| GPT-3.5 Turbo | Simple tasks, high volume | Low | Fast |
Parameters
- Temperature (0-2) - Controls randomness
- Lower (0-0.3) - More deterministic
- Higher (0.7-1) - More creative
- Max Tokens - Maximum response length
- Top P - Alternative to temperature
- Frequency Penalty - Reduce repetition
- Presence Penalty - Encourage new topics
Pricing
Check OpenAI Pricing for current rates.
Cost Optimization
- Use GPT-3.5 Turbo for simple tasks
- Use GPT-4 Turbo for most coding tasks
- Reserve GPT-4o for complex, multimodal tasks
Rate Limits
OpenAI has rate limits based on your plan:
- Free Tier - Limited requests per minute
- Pay-as-you-go - Higher limits
- Enterprise - Custom limits
Monitor usage at platform.openai.com/usage.
Troubleshooting
Invalid API Key
- Verify your API key is correct
- Check if the key is active
- Ensure you have sufficient credits
Rate Limit Exceeded
- Wait a moment and retry
- Consider upgrading your plan
- Implement backoff in automated scripts
Model Not Available
- Check if the model is enabled in your account
- Some models require specific API tiers