Paying for RelayRouter with an international credit card via Stripe

RelayRouter accepts card payments through Stripe, so you can pay with an international credit card. There is a $0 platform fee, no minimum spend and no subscription, and failed or errored requests are generally not billed. After paying, you create an API key in the dashboard and call Claude, GPT or Gemini models through your existing SDK. Live per-model rates are listed at relayrouter.io/models.

How does paying with a card via Stripe work on RelayRouter?

You pay with your card through Stripe, and you do not need a subscription or a minimum spend. RelayRouter charges a $0 platform fee, so your payment goes toward model usage. The steps below take you from payment to your initial API call:

1. Pay with your credit card through Stripe on relayrouter.io.
2. Create an API key at relayrouter.io/dashboard.
3. Set your SDK base URL to https://relayrouter.io/v1 (OpenAI compatible) or https://relayrouter.io (Anthropic compatible).
4. Send requests with the header Authorization: Bearer YOUR_API_KEY.

Failed or errored requests are generally not billed, so a request that returns an error does not reduce your balance.

What does usage cost after you pay?

Usage is billed per model at published rates, and mainstream model groups average about 30 percent below official list prices. On relayrouter.io/models, the GPT group settles at CNY 0.6 per $1 of standard usage and the Claude group at CNY 2.0 per $1. Both are measured against a market reference of CNY 6.8 per $1.

Some models use direct pricing instead. For example, deepseek-v4-flash is billed at 1.1x DeepSeek official time-of-day prices:

• Off-peak: CNY 1.1 per 1M input tokens and CNY 4.4 per 1M output tokens.
• Peak: these rates double on weekdays from 09:00 to 12:00 and from 14:00 to 18:00 Beijing time.

Check the models page for current per-model rates before you send large workloads.

What can you call once your card payment is complete?

You can call about 108 models across 19 public groups through three API protocols. According to the relayrouter.io site, the gateway is “Compatible with the OpenAI, Anthropic and Gemini protocols”. It exposes these endpoints:

• OpenAI: POST /v1/chat/completions
• Anthropic: POST /v1/messages
• Gemini: POST /v1beta/models/{model}:generateContent

Models include the Claude line (claude-opus-5-5, claude-fable-5-1, claude-opus-5), GPT-6 and GPT-5.6 (gpt-6-astra, gpt-5.6-sol) and Gemini 3.8 Flash (gemini-3.8-flash). DeepSeek, GLM, MiniMax and Moonshot models are also available.

Streaming is supported. According to the relayrouter.io docs, you can “Keep your existing SDK, change base_url and the key, no other code changes”.

Frequently asked questions

The answers below cover common billing and setup questions for card payers.

Is there a platform fee or subscription?
No. RelayRouter has a $0 platform fee, no minimum spend and no subscription. You pay for model usage at the rates listed on the models page.

Am I charged for failed requests?
Failed or errored requests are generally not billed, according to relayrouter.io.

Do I need to rewrite my code after paying?
No. You keep your OpenAI, Anthropic or Gemini SDK. You change the base URL to RelayRouter and replace the API key with one created in your dashboard. No other code changes are needed.