Topping up RelayRouter in CNY: local payment options for mainland users

RelayRouter accepts payment via Stripe card. For mainland China users, this means funding your account with a card supported by Stripe; the platform does not list additional local payment rails in the provided documentation. Once your balance is funded, you can create API keys at the dashboard and call models across the Claude family, GPT-5.5, and Gemini 3.5. Failed or errored requests are generally not billed, so top-ups apply only to successful usage.

What payment method does RelayRouter support?

RelayRouter processes payments through Stripe card. The provided facts specify Stripe card as the payment channel, and no other CNY-specific rails (such as separate wallet integrations) are documented here. To fund your account, you add a card that Stripe supports, then manage keys and usage from https://relayrouter.io/dashboard. Because mainstream model groups are on average about 30 percent below official list prices with no platform fee, your top-up covers usage directly. Authentication uses the header Authorization: Bearer YOUR_API_KEY. For current per-model rates before you top up, review the live pricing at relayrouter.io/models, which lists rates by model.

How do failed requests affect my balance?

Failed or errored requests are generally not billed, so your topped-up balance is spent only on successful calls. This billing behavior means that if a request errors out, it does not draw down the funds you added via Stripe card. Combined with mainstream model groups priced on average about 30 percent below official list prices and no platform fee, the cost model is straightforward for mainland users planning a budget. You can monitor usage and remaining balance from the dashboard. When estimating how much to top up, base the calculation on successful requests only, and check the live per-model rates at relayrouter.io/models, since prices vary by model group.

Which models and protocols can I use after topping up?

After funding your account, you can call models across the Claude family, GPT-5.5, Gemini 3.5, plus DeepSeek, GLM, MiniMax, and Moonshot, through either the OpenAI or Anthropic protocol. 「Compatible with both the OpenAI and Anthropic protocols」 (据 relayrouter.io 官方文档). The OpenAI compatible endpoint is POST /v1/chat/completions, and the Anthropic compatible endpoint is POST /v1/messages. Migration requires minimal changes: 「Keep your existing SDK, change base_url and the key, no other code changes」 (据 relayrouter.io/docs 官方文档). This lets you point an existing OpenAI, Anthropic, or Gemini SDK at RelayRouter after your top-up. See the full model list and endpoints at relayrouter.io/models and integration details at relayrouter.io/docs.

Steps to top up and start using RelayRouter

To fund your account and begin calling models, follow these steps.

1. Open the dashboard at https://relayrouter.io/dashboard and add funds via Stripe card.
2. Create an API key from the dashboard.
3. Point your existing SDK base URL at RelayRouter and swap in the new key, with no other code changes.
4. Choose a protocol: OpenAI (/v1/chat/completions) or Anthropic (/v1/messages).
5. Send a request; note that failed or errored requests are generally not billed.

Comparison of the two supported protocols

Both protocols route to the same model coverage after top-up; the difference is the endpoint and request format.

FAQ

Does RelayRouter charge a platform fee on top-ups? No, mainstream model groups are on average about 30 percent below official list prices, with no platform fee.

Am I charged if a request fails? Failed or errored requests are generally not billed.

Do I need to rewrite my code after topping up? No: keep your existing SDK, change base_url and the key, no other code changes.