About SeedRouter
SeedRouter is one API key that reaches image, video, language and audio models from several vendors. You top up a balance in US dollars, every model is charged per request at its listed price, and a request that fails is not charged.
Why SeedRouter exists
Shipping an AI feature used to mean one account, one key and one invoice per model vendor, and swapping a model meant rewriting the integration. SeedRouter removes that: the request shape, the key and the balance stay the same whichever model you call, so choosing a model becomes a product decision instead of an integration project.
How SeedRouter works
One key
A single API key reaches every model on SeedRouter. Create and revoke keys from the dashboard.
One balance
Top up in US dollars and spend it across every model. There is no subscription and no monthly minimum.
One request shape
Language models are served through an OpenAI-compatible endpoint, so existing SDKs work by changing the base URL. Image, video and audio jobs return a task id you can poll or receive by webhook.
One bill
Every request is recorded with the model, the time and the price, so usage and cost are auditable in one dashboard.
What we will not do
- Charge for a request that failed.
- Hide a model price behind a quote or a sales call.
- Use your prompts or outputs to train models of our own.
- Change your integration when a model is added or retired.
Common questions about SeedRouter
What is SeedRouter?
SeedRouter is an API platform that puts image, video, language and audio models behind one API key and one prepaid balance, billed per request at each model’s listed price.
Who is SeedRouter for?
Teams and individual developers who ship AI features in a product and do not want a separate account, key and invoice for every model vendor.
How much does SeedRouter cost?
There is no subscription. You top up a balance in US dollars and each request is charged at the listed price of the model you call. Failed requests are not billed.
What happens when a model is unavailable?
The request returns an error instead of a result and you are not charged for it. You can retry when the model is back, or send the same request to another model with the same key.
Can I keep using the OpenAI SDK?
Yes. Language models are served through an OpenAI-compatible endpoint, so an existing integration moves by changing the base URL and the key.
Talk to us
Questions about models, billing or an integration reach a human at this address.