machined.
Machined V2
Machined V2
  • About
  • Quickstart
  • Change log
    • 2025-05-29: Heading Style
    • 2025-05-25: Machined V3 beta
    • 2025-04-01: Brand Voice beta
    • 2025-03-24: Bulk Research, Language fixes and more
    • 2025-03-16: Stability AI images
    • 2025-02-22: Improvements and bug fixes
    • 2025-01-14: Reduced costs
    • 2024-12-26: Projects
    • 2024-12-10: Improvements and bug fixes
    • 2024-11-12: Custom Outlines GTM
    • 2024-10-06: Humanizer GTM
    • 2024-09-23: Model updates
    • 2024-09-10: Custom Outlines beta
    • 2024-08-25: UX Improvements
    • 2024-08-17: Humanizer improvements
    • 2024-07-22: GPT-4o-mini
    • 2024-06-12: Humanizer beta
  • Who is Machined for?
    • Startups
    • Niche Site Owners
    • SEO Marketing Agencies
  • Walkthrough
    • Configuring OpenAI API Keys
    • Connecting to WordPress
    • Connecting to Webflow
    • Creating Clusters
      • Auto-Pilot Clusters
      • Manual Clusters
    • Writing Articles
    • Featured Images
    • Publishing
      • Publishing to WordPress
      • Publishing to Webflow
    • Exporting
      • Copy as Rich Text
      • Download as HTML
      • Download as Markdown
      • Download Featured Images
    • Webhooks
    • Research
  • Troubleshooting
    • OpenAI API Key
    • WordPress integration
  • IMAGES
    • Stability AI
    • DALL-E 3
    • Stock Photos
  • Features
    • Experimental Features
    • Clusters
    • Auto-pilot
    • Keyword Metrics
    • Topic
    • Audience
    • Language
    • Length
    • AI Model
    • Perspective
    • Tone of Voice
    • Internal Linking
    • Research
    • Humanizer
    • Custom Outlines
  • SEO Strategy
    • Internal Linking
    • External Linking
    • Topical Authority
    • Content Clusters
    • Long-tail Keywords
    • Keyword Cannibalization
    • Reader Engagement
    • Bounce Rate
Powered by GitBook
On this page
  • Troubleshooting
  • Intermittent Errors
  • Rate Limits
  • Storage and Security

Was this helpful?

  1. Troubleshooting

OpenAI API Key

PreviousResearchNextWordPress integration

Last updated 8 months ago

Was this helpful?

Machined allows you to generate an unlimited number of content clusters and articles for an insanely low cost. We are able to do this by offloading the AI costs directly to you, the user. In essence, you pay for your own AI usage directly with OpenAI. This means that you will need to manage your own OpenAI account and provide your own API keys.

Follow our guide to .

Troubleshooting

If you experience errors writing articles, the most common issues are related to the OpenAI account and/or the keys being used, or their service status.

  1. Ensure you have an (credit card on file)

  2. Ensure you have if you intend to use it

  3. Check whether there are any

  4. Check whether your account is

Please be aware that some errored articles may still incur a token cost if errors occur midway through structuring or writing articles.

Intermittent Errors

OpenAI APIs often experience intermittent errors. Sometimes certain models have slow response times, sometimes models are unresponsive and at times the entire API might be unavailable. You can check the for more info, but bear in mind that it is usually updated retrospectively rather than in real time.

Please note that there is nothing we can do to circumvent intermittent OpenAI errors, please keep a close eye on their status page and reach out if you are experiencing unexpected errors.

Rate Limits

Please note that our backoff strategy will only retry up to a certain number of times before quitting with a final error.

Storage and Security

Once a key is set, it is never stored or transferred in plan text. Furthermore, two separate security secrets which are stored on separate servers are needed to decrypt the key on each usage.

OpenAI imposes rate limits on all accounts, this prevents any one account from making too many requests and impacting the service for others, and allows OpenAI to better manage their infrastructure and services. These rate limits are imposed on all API calls with the use of specific errors (called a 429 response) that tell the caller that they have breached a rate limit and to slow down with requests. You can read more about on the OpenAI webpage.

Machined will deal with most rate limits using what's called an exponential backoff strategy as . In essence, when OpenAI tells us that we are making too many requests, we back off from making further requests for a short time. Doing this allows us to write articles in the fastest way possible while also taking measures to not overwhelm your OpenAI account, and not compromise your account's standing with OpenAI.

Your api keys are encrypted at rest and in transit using (Advanced Encryption Standard), the same standard used by the to protect their own files.

rate limits
recommended by OpenAI
AES-256
US Government
configuring your api keys
OpenAI Status Page
intermittent errors
rate limited
OpenAI Status Page
OpenAI Developer account with billing enabled
access to GPT-4