Model APIs

Articles

• How do I control reasoning?
• Which OpenAI API features are supported?
• What happens when a model is deprecated or retired?
• Why is my first request slower than the rest?
• Can I call the API directly from my frontend? (CORS errors)
• Where do I see logs for my Model API requests?
• How do I get access to a model that isn't in my workspace?
• Why did I get a 5xx error, and should I retry?
• How does prompt caching work, and how do I know if I'm getting cache hits?
• How do I track usage and spend per model?