How can we help you?

Search our knowledge base, browse categories, or submit a ticket to our AI support team.

🔍
All API & SDK Models Billing Account

Browse by Category

View all guides →
24 articles 🔌

API & SDK

Authentication, rate limits, endpoints, and language-specific SDK usage.

18 articles 🧠

Model Configuration

Fine-tuning, prompt engineering, temperature settings, and output parsing.

12 articles 💳

Billing & Usage

Token pricing, invoice management, quota increases, and payment methods.

15 articles 👤

Account & Security

API key rotation, 2FA setup, team roles, and organization management.

9 articles ⚙️

Webhooks & Streaming

Real-time event handling, SSE configuration, and payload debugging.

7 articles 🔒

Safety & Moderation

Content filtering, compliance guidelines, and custom guardrails.

Popular Articles

How to handle 429 Rate Limit errors
Fine-tuning NexusAI v3 on custom datasets
Understanding tokenization & pricing
Streaming responses with Server-Sent Events
Rotating API keys without downtime

Frequently Asked Questions

What are the current rate limits for free vs paid tiers?
Free tiers are limited to 60 requests per minute with a 10k token context window. Professional plans scale to 500 RPM, and Enterprise offers custom limits up to 5,000 RPM with dedicated throughput allocation.
How do I access my usage metrics and token consumption?
Navigate to Dashboard → Usage & Analytics. You can view real-time token consumption, request latency, and download CSV exports for billing reconciliation. Enterprise clients get dedicated analytics endpoints.
Is my data stored or used for model training?
No. All API requests are processed in memory. We do not retain your prompts, completions, or uploaded files for training purposes. Data is encrypted in transit and at rest, and fully deleted after response delivery.
How long does fine-tuning typically take?
Most fine-tuning jobs complete within 2-6 hours depending on dataset size and base model. You'll receive a webhook notification or dashboard alert when your custom model is ready for inference.

Still need help?

Support Channels

📧

Email Support

support@nexusai.tech
Response time: < 4 hours

💬

Live Chat

Available 24/7 in the dashboard
Average wait: < 2 minutes

📚

Developer Docs

nexusai.tech/docs
API reference, SDKs, examples

🌐

Community Forum

Discuss issues, share solutions,
connect with other developers

Submit a Support Ticket

All Systems Operational
Last checked: Just nowView detailed status →