seedrouter

What is SeedRouter

SeedRouter is a unified API platform that provides access to image, video, language, and audio AI models through a single API key. It replaces separate accounts, keys, and invoices for each model vendor with a single integration. The platform offers pay-per-request billing, and failed requests cost nothing.

How to use SeedRouter

1. Create a SeedRouter account and obtain your API key.
2. Load a balance in USD to your account.
3. Send requests to any supported model using the same request shape and billing.
4. For language models, use the OpenAI-compatible endpoint by pointing your OpenAI SDK to SeedRouter and using your SeedRouter key.
5. For video and other long-running jobs, the request returns a task ID; poll it or register a webhook, and the output arrives as a CDN link when ready.

Features of SeedRouter

• One API key for image, video, language, and audio models.
• Pay-per-request billing with no subscription or monthly minimum.
• Failed requests are not charged.
• OpenAI-compatible endpoint for language models.
• Webhooks for long-running jobs.
• Per-request billing that can be audited.
• Supports models from providers such as Anthropic, ByteDance, Google, OpenAI, Alibaba, MiniMax, xAI, DeepSeek, and others.
• Model families include GPT, Claude, Gemini, GPT Image, Seedance, Flux, and Qwen Image.

Use Cases of SeedRouter

• Developers building products that require multiple AI capabilities (image generation, video creation, language processing, audio) without managing multiple vendor accounts.
• Production applications needing reliable, auditable per-request billing and webhook support for long-running tasks.
• Teams wanting to switch between models easily using the same request shape and key.

Pricing

• Every model has a listed price: per request, per image, per second of video, or per token.
• You are charged only when the output is delivered; failed requests cost nothing.
• No subscription and no monthly minimum.
• Top up a balance in USD and spend it across every model; unused balance stays in your account.
• Examples: Claude Fable 5.1 from $8.00 per 1M input tokens; Seedance 2.0 from $0.0909 per second; Nano Banana 2 from $0.03 per image; GPT Image 2.5 from $0.00448 per image.

FAQ

What is SeedRouter? SeedRouter is one API in front of image, video, language and audio models. You create one key, load a balance and call any model with the same request shape and the same billing. It replaces separate accounts, keys and invoices for each model vendor with a single integration.

How does SeedRouter pricing work? Every model on SeedRouter has a listed price: per request, per image, per second of video or per token. You are charged when the output is delivered and nothing for failed requests. There is no subscription and no monthly minimum.

What happens when a model is unavailable? The request returns an error instead of a result, and you are not charged for it. Retry when the model is back, or send the same request to another model on SeedRouter with the same key and the same request shape.

Can I keep using the OpenAI SDK with SeedRouter? Yes. Language models are served through an OpenAI-compatible endpoint. Point the SDK at SeedRouter, use your SeedRouter key and keep your existing code.

How do video and other long-running jobs work on SeedRouter? Video and some image and audio models run as tasks. The request returns a task id; poll it or register a webhook, and the output arrives as a CDN link when it is ready.

Which models does SeedRouter support? Image, video, language and audio families, including GPT, Claude, Gemini and GPT Image, plus video and image families such as Seedance, Flux and Qwen Image. The full list with prices is on the models page, and it grows without changes on your side.

Do I need a subscription to use SeedRouter? No. Top up a balance in USD and spend it across every model on SeedRouter. Unused balance stays in your account.

Is SeedRouter suitable for production traffic? Yes. SeedRouter is built for products, not demos: per-request billing you can audit, webhooks for long jobs, and no charge for requests that fail.