All Systems Operational

How can we help you?

Search our knowledge base, documentation, or community forums.

🔍

Browse by Topic

📚

Documentation

Comprehensive guides, tutorials, and best practices for building with NexusAI.

View Guides →
🔌

API Reference

Detailed endpoints, request formats, and SDK implementations.

Explore API →
🔑

Account & Billing

Manage your subscription, payment methods, and usage limits.

Manage Account →
🛡️

Security & Auth

API keys, OAuth flows, role-based access, and compliance.

Learn Security →
🐛

Troubleshooting

Common errors, latency issues, and model failure codes.

Fix Issues →
💬

Community

Discord, forums, and developer stories from other users.

Join Discussion →

Frequently Asked Questions

How do I reset my API key?
You can reset your API key from the Dashboard under Settings > Security. Rotating your key will immediately invalidate the old one. We recommend updating your application environment variables immediately after rotation.
What is the rate limit for the Standard plan?
The Standard plan allows for 60 requests per minute (RPM) and 1,000 requests per hour (RPH). If you exceed this, you will receive a 429 Too Many Requests error. You can upgrade to the Pro plan for higher limits or request a custom enterprise agreement.
Why is my inference latency high?
Latency can be caused by high traffic loads, complex prompt structures, or specific model configurations. Check the Status Page for regional outages. For persistent issues, please submit a ticket with your Request ID found in the API response headers.
How do I export my conversation history?
Navigate to the Playground, select the project you wish to export, and click the "Actions" menu. Choose "Export JSON" or "Export CSV". For enterprise accounts, you can configure automated S3 bucket syncing via the API.

Still need help? Open a Ticket

We typically respond within 24 hours for Standard plans and 4 hours for Enterprise.