Support

How do I get an API key?

Sign up at console.wazza.ai and generate an API key from your dashboard. New accounts receive free credits to get started.

What are the rate limits?

Rate limits vary by plan:

• Free: 50 requests/hour
• Pro: 500 requests/hour
• Team: 2,000 requests/hour
• Enterprise: 10,000+ requests/hour

How does credit pricing work?

Different models and capabilities have different credit costs. For example:

• Text-to-image (FLUX): 1-3 credits
• Text-to-video (Sora): 10-15 credits
• Text-to-speech (ElevenLabs): 1-3 credits
• 3D generation (Genie 3): 15-30 credits

View detailed pricing in the Model Catalog.

How long do generation jobs take?

Generation times vary by content type and model:

• Images: 5-30 seconds
• Videos: 2-15 minutes
• Audio: 5-20 seconds
• 3D Models: 5-20 minutes

Use webhooks for long-running operations instead of polling.

Can I use the Chat Orchestrator instead of choosing models?

Yes! The Chat Orchestrator uses Claude 4.5 Sonnet to understand your natural language request and automatically select the best model, provider, and parameters. This is the easiest way to get started. Learn more

What happens if a provider is down?

Wazza Engine automatically monitors provider health and can route requests to alternative providers. You can also implement fallback logic in your application. Check real-time status at status.wazza.ai

Do you offer enterprise plans?

Yes! Enterprise plans include custom rate limits, dedicated support, SLA guarantees, and volume discounts. Contact enterprise@wazza.ai for pricing.

How do I report a bug or request a feature?

For bugs and feature requests, please email support@wazza.ai with details and request IDs. Our team reviews all feedback and implements highly requested features in future releases.