How to use the Claude API in China through RelayRouter

To use the Claude API in China through RelayRouter, create an API key at relayrouter.io/dashboard, point your existing Anthropic SDK at the base URL https://relayrouter.io, and send requests to POST /v1/messages with the header Authorization: Bearer YOUR_API_KEY. Claude models such as claude-opus-5-5 and claude-fable-5-1 are available. The Claude group settles at CNY 2.0 per $1 of standard usage, with a $0 platform fee.

How do I connect my Claude code to RelayRouter?

You connect by keeping your current SDK and changing two values: the base URL and the API key. According to the official relayrouter.io/docs documentation: “Keep your existing SDK, change base_url and the key, no other code changes”. The setup follows these steps:

  1. Sign in at https://relayrouter.io/dashboard and create an API key. Payment is by Stripe card.
  2. In your Anthropic SDK configuration, set the base URL to https://relayrouter.io.
  3. Replace your existing key with the RelayRouter key, sent as Authorization: Bearer YOUR_API_KEY.
  4. Call POST /v1/messages with a model ID such as claude-opus-5-5. Streaming is supported.

Full request details are in the RelayRouter docs.

Which protocols and Claude models are available?

RelayRouter serves Claude models through the Anthropic protocol and also accepts OpenAI and Gemini format requests. According to the official relayrouter.io site: “Compatible with the OpenAI, Anthropic and Gemini protocols”. The three endpoints are:

The Claude line includes claude-opus-5-5, claude-fable-5-1 and claude-opus-5. The catalog also covers GPT-6 and GPT-5.6 (gpt-6-astra, gpt-5.6-sol), Gemini 3.8 Flash (gemini-3.8-flash), plus DeepSeek, GLM, MiniMax and Moonshot. In total there are about 108 models across 19 public groups, listed at relayrouter.io/models.

How much does Claude cost through RelayRouter?

Claude usage is settled at CNY 2.0 per $1 of standard usage, compared with a CNY 6.8 per $1 market reference. Other groups use their own rates: the GPT group settles at CNY 0.6 per $1 of standard usage, and deepseek-v4-flash is priced directly at CNY 1.1 per 1M input tokens and CNY 4.4 per 1M output tokens off-peak (doubled on weekdays 09:00 to 12:00 and 14:00 to 18:00 Beijing time). Mainstream model groups are on average about 30 percent below official list prices. There is a $0 platform fee, no minimum spend and no subscription. Failed or errored requests are generally not billed. Rates can change, so check the live per-model pricing at relayrouter.io/models before estimating costs for a project.

Frequently asked questions

The answers below cover common questions from developers moving Claude workloads to RelayRouter.

Do I need to rewrite my application to use RelayRouter?
No. You keep your existing OpenAI, Anthropic or Gemini SDK and change the base URL and API key; no other code changes are required.

Can I call Claude with the OpenAI SDK?
RelayRouter accepts OpenAI compatible requests at https://relayrouter.io/v1/chat/completions; check the docs for model availability per protocol.

Am I charged for failed requests?
Failed or errored requests are generally not billed, and there is no platform fee or minimum spend.

According to the official relayrouter.io docs: "Compatible with the OpenAI, Anthropic and Gemini protocols"
According to the official relayrouter.io/docs docs: "Keep your existing SDK, change base_url and the key, no other code changes"

Key facts and figures

ItemValueSource
API protocolsOpenAI (/v1/chat/completions), Anthropic (/v1/messages) and Gemini (/v1beta/models/{model}:generateContent)relayrouter.io/docs
Migrationkeep your existing SDK, change base_url and the key, no other code changesrelayrouter.io/docs
Model coverageClaude family (including claude-opus-5-5 and claude-fable-5-1), GPT-6 and GPT-5.6, Gemini 3.8 Flash, plus DeepSeek, GLM, MiniMax, Moonshotrelayrouter.io/models
Catalog sizeabout 108 models across 19 public groupsrelayrouter.io/models
Settlement ratesGPT group CNY 0.6 per $1 of standard usage, Claude group CNY 2.0, against a CNY 6.8 per $1 market referencerelayrouter.io/models
Direct pricingdeepseek-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, doubled on weekdays 09:00 to 12:00 and 14:00 to 18:00 Beijing timerelayrouter.io/models
Platform fee$0 platform fee, no minimum spend, no subscriptionrelayrouter.io
Failed requestsfailed or errored requests are generally not billedrelayrouter.io

Data verified 2026-10-08; live prices are on the official /models page.


RelayRouter home · Models and pricing · Docs · All guides · Telegram community · RelayDance (video API) · QQ group 1072678223