WaveSpeed User Guide & FAQ
WaveSpeed is a high-performance platform for AI image and video generation. We host a curated collection of state-of-the-art models that support text-to-image, image-to-video, text-to-video, and more.
1. Important Policies
Commercial Use & Privacy
- All models are licensed for commercial use — Check each model’s README for specific license details.
- We do NOT store your data or use it to train AI
- All user-generated content is automatically deleted after 7 days — Download and save any files you want to keep.
Content Policy
Prohibited content: Illegal activities, hateful content, child exploitation, non-consensual intimate imagery, weapons development.
Violation of these policies may result in immediate account termination.
Age restriction: Our services are not intended for users under 13 years old.
See full Terms of Service | Privacy Policy
Refund Policy
- No refunds for incorrect parameters — If results are unsatisfactory due to user input errors, refunds will not be provided. Read the model’s README carefully before running.
- We do not guarantee model output quality — Each model has its own limitations. Results depend on your use case and inputs.
- Refunds for system errors only — We only compensate for system-level failures. Most refunds are processed automatically within 3 hours.
- Failed requests are refunded — Automatically returned to your credits within 3 hours.
- Credits are non-refundable — Purchased credits cannot be exchanged for cash, but they never expire.
Reporting Issues
If you believe there’s a technical problem:
- Go to Predictions
- Copy the Task ID (shown in the ID column)
- Provide it to our support team
2. Registration & Login
How do I register?
Sign in using your Google or GitHub account at wavespeed.ai. No separate registration required.
What if I forget my password?
WaveSpeed uses third-party authentication. Reset your password on the respective platform:
Are other login options supported?
Currently, only Google and GitHub accounts are supported.
3. Account & Billing
What payment methods are accepted?
We currently support:
- Stripe (credit/debit cards)
- PayPal
- WeChat Pay / Alipay
- Naver Pay
We are actively exploring more payment options.
How do I add credits?
Go to Top Up to select your preferred payment method. You can also redeem coupons and generate invoices from this page.
Do credits expire?
No. Your credit balance never expires.
Can I withdraw or transfer credits?
- Free trial credits: Cannot be withdrawn or transferred.
- Purchased credits: Contact support@wavespeed.ai with both old and new account email addresses to request a transfer.
How is pricing calculated?
- Pricing is usage-based and varies by model.
- The estimated price is shown on the “Run” button before generation.
- Final charge may vary slightly from the estimate.
Are your prices competitive?
Yes. For open-source models, our pricing matches the original providers — fully transparent. For closed-source models, we guarantee prices at or below market average. Best value, no hidden fees.
Can I get invoices?
Yes. For invoice requests, email support@wavespeed.ai with your expected usage volume.
Do you offer discounts?
Yes, for high-volume customers. Contact support@wavespeed.ai to apply.
How do I delete my account?
Contact support@wavespeed.ai. Note: Once terminated, you will lose access to all services and data.
4. Using the Services
How do I use the platform?
- Browse models at wavespeed.ai/models
- Select a model and enter your parameters
- Click “Run” to generate
- View results in Predictions
How long does processing take?
Processing time varies by model and input complexity. Simple tasks complete in seconds; complex tasks take longer. Track progress in the Predictions page.
How long are my generated files stored?
All outputs are stored for 7 days. After that, files may be deleted at any time. Download and save any files you want to keep.
Can I use outputs commercially?
Most models are available for commercial use. Check the README section on each model page for specific license details.
How can I improve my prompts?
Use the Prompt Enhancer feature — it automatically optimizes your prompt for better results. Located next to the prompt input field on each model page. Cost: $0.001 per use.
Does WaveSpeed offer an API?
Yes. See our API Documentation for details. Each model page includes code examples in cURL, Python, and JavaScript.
Can I create multiple API keys?
Yes. You can create and manage multiple API keys from the API Keys page. This is useful for separating access across different projects or team members.
Can I batch requests?
Not yet. Requests are handled one at a time. Batch processing may be supported in future releases.
5. API Rate Limits
Our API rate limits are divided into tiers based on your account level:
| Level | Images/min | Videos/min | Concurrent Tasks | How to Activate |
|---|---|---|---|---|
| Bronze | 10 | 5 | 3 | Default for new users |
| Silver | 500 | 60 | 100 | One-time top-up of $100 |
| Gold | 3,000 | 600 | 2,000 | One-time top-up of $1,000 |
| Ultra | 5,000 | 5,000 | 5,000 | One-time top-up of $10,000 |
What do these numbers mean?
- Images/min & Videos/min: The maximum number of generations you can start per minute. Higher tiers can submit more requests in the same time period.
- Concurrent Tasks: How many tasks can run at the same time. For example, Bronze users can only have 3 tasks processing simultaneously — if you submit a 4th, it will wait until one finishes.
How do I upgrade my tier?
Tiers upgrade automatically when you reach the top-up threshold. For example, once your total top-ups reach $100, you’re automatically upgraded to Silver. No action needed — just add credits.
What if I need higher limits?
For enterprise customers requiring limits beyond Ultra tier, contact support@wavespeed.ai for custom solutions.
6. Troubleshooting
My generation failed. What should I do?
- Check your parameters — Some models have specific requirements (e.g., image dimensions, file formats). Read the model’s README.
- Check your balance — Ensure you have sufficient credits.
- Try again — Temporary issues may resolve on retry.
- Report the issue — Copy the Task ID from Predictions and contact support.
Failed requests are automatically refunded within 3 hours.
My API key doesn’t work. Why?
API keys require a top-up to activate. Keys generated before your first top-up will not work. Add credits to your account, then try again.
Also check:
- The key is copied correctly (no extra spaces)
- The key hasn’t been deleted or regenerated
- You’re using the correct header format:
Authorization: Bearer YOUR_API_KEY
I’m getting “Too Many Requests” errors.
You’ve hit your tier’s rate limit. Options:
- Wait — Limits reset every minute.
- Upgrade — Add credits to reach the next tier threshold.
- Optimize — Reduce concurrent requests or add delays between calls.
See API Rate Limits for tier details.
Why is my output quality poor?
- Use Prompt Enhancer — It optimizes your prompt for better results ($0.001/use).
- Check model parameters — Resolution, steps, and other settings affect quality.
- Choose the right model — Different models excel at different tasks. Try a few to find the best fit.
- Provide clear prompts — Be specific and descriptive.
7. Data Security & Privacy
How is my data protected?
We use advanced encryption to secure your data and adhere to data protection regulations. Our servers undergo regular security audits.
Is my data shared with third parties?
No. We never share your personal information or uploaded data with third parties without explicit authorization, unless required by law.
8. Technical Support
How can I get help?
- Live Chat: Click the chat icon in the bottom-right corner of our website
- Email: support@wavespeed.ai
- Discord: Join our community
- X (Twitter): @wavespeed_ai
Note: Support handles technical issues only. Please do not ask support to generate content for you.
We’re committed to giving every user complete and personalized support. If our response is delayed, it’s because we’re carefully handling another case — thank you for your patience.
How do I submit feedback?
We welcome feedback on product experience and feature improvements. Use any of the support channels above.