Frequently Asked Questions

AsteroidRouter is a unified AI gateway that provides access to 300+ cutting-edge models from leading providers (OpenAI, Anthropic, Google, Meta, etc.) through a single, OpenAI-compatible API endpoint. We simplify the complexity of managing multiple API keys and varying integration standards.

1. Create a free account on our dashboard. 2. Generate an API key. 3. Replace your current provider's base URL with https://inference-api.asteroidrouter.ai/v1 and use your AsteroidRouter API key. No credit card is required to start with the free tier.

Yes. AsteroidRouter is designed to be a drop-in replacement for the OpenAI API. You can use official OpenAI SDKs (Python, Node.js, etc.) or any HTTP client by simply updating the base_url and api_key.

AsteroidRouter uses a credit-based system. You can purchase credits using Alipay, WeChat Pay, UnionPay, Credit Cards, as well as Stripe, PayPal, and other major payment methods. Credits are then consumed based on your actual token usage. Pricing per 1k or 1M tokens for each model is fully transparent and can be viewed in our Models Catalog.

AI model pricing is dynamic and may adjust over time due to several factors: upstream provider pricing changes, compute demand during peak periods, model optimization improvements that we pass on as savings, and fluctuations in underlying resource costs (electricity, hardware).

We accept payments through Alipay, WeChat Pay, UnionPay, Credit Cards, Stripe, and PayPal. In addition, users with subscription plans receive their credit allowance automatically according to their plan terms.

The Models page shows the request model names you should send in the model parameter. Overview may show the billed execution variant used for the request, which can appear as seedance-2.0-asset or seedance-2.0-asset-fast. This is expected behavior. When calling the API, continue using seedance-2.0 or seedance-2.0-fast unless the Models page explicitly lists a different request model.

When using models hosted in different geographic regions, you may encounter occasional instability due to cross-border latency, regional outages at the provider's end, upstream API rate limiting during peak hours, or regional network filtering and throttling.

We actively monitor the health of all supported models. If a specific provider is experiencing a "partial outage," our gateway may automatically attempt to route your request through a healthier instance or provide a clear error message so your application can fail gracefully or switch to a fallback model.

Yes. We support Server-Sent Events (SSE) streaming for all compatible chat and completion models, ensuring a responsive user experience for real-time applications.

No. We do not store the content of your prompts or the generated completions. We only log usage metadata (such as token counts, model IDs, and timestamps) for billing, rate limiting, and analytics purposes.

Our full privacy policy is available at asteroidrouter.ai/privacy-policy.

No. Once deposited or earned through an AsteroidRouter token plan, your credits remain in your account indefinitely until they are consumed by API usage.

All credit purchases are final due to the nature of on-chain transactions. However, if you experience technical issues that prevented you from using purchased credits, please contact support@asteroidclothing.com for a case-by-case review.

1. Check our status page or the upstream provider's status. 2. If the issue persists for more than a few minutes, try switching to a different model (e.g., from a US-based model to a local/regional alternative). 3. Contact our technical support for investigation.

For technical issues, account inquiries, or custom enterprise limits, please email us at support@asteroidclothing.com. Our team typically responds within 24 hours during business days.