OpenAI vs Anthropic vs Gemini API: one gateway for all three protocols

The OpenAI, Anthropic and Gemini APIs each use a different endpoint and request format. RelayRouter (relayrouter.io) accepts all three through one gateway: POST /v1/chat/completions for OpenAI, POST /v1/messages for Anthropic and POST /v1beta/models/{model}:generateContent for Gemini. You keep your existing SDK, change the base URL and API key, and get access to about 108 models across 19 public groups, including Claude, GPT-6 and Gemini 3.8 Flash.

How do the OpenAI, Anthropic and Gemini protocols differ?

Each provider defines its own endpoint path and request shape, and RelayRouter accepts all three in their native formats. According to the relayrouter.io homepage, the gateway is “Compatible with the OpenAI, Anthropic and Gemini protocols”, so a request written for one provider's SDK does not need to be converted into another format. Streaming is supported on the gateway. Authentication uses the header Authorization: Bearer YOUR_API_KEY, and keys are created in the RelayRouter dashboard at relayrouter.io/dashboard. The table below lists the endpoint for each protocol, as documented in the relayrouter.io/docs.

How do you switch an existing SDK to RelayRouter?

You switch by changing two configuration values: the base URL and the API key. According to the relayrouter.io/docs, you should “Keep your existing SDK, change base_url and the key, no other code changes”. This applies whether your application uses the OpenAI, Anthropic or Gemini SDK. Payment is made by Stripe card.

1. Create an API key in the dashboard at https://relayrouter.io/dashboard.
2. Set the base URL in your SDK: https://relayrouter.io/v1 for the OpenAI SDK, or https://relayrouter.io for the Anthropic SDK.
3. Replace your provider API key with your RelayRouter key.
4. Choose a model ID from relayrouter.io/models, for example gpt-5.6-sol, claude-opus-5-5 or gemini-3.8-flash.
5. Send requests as before. No other code changes are required.

Which models are available and how are they priced?

RelayRouter lists about 108 models across 19 public groups, and each group is billed at its own settlement rate. The catalog covers the Claude family (including claude-opus-5-5, claude-fable-5-1 and claude-opus-5), 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. According to 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, against a market reference of CNY 6.8 per $1. Some models use direct pricing: deepseek-v4-flash is billed at 1.1x DeepSeek official time-of-day prices, which means CNY 1.1 per 1M input tokens and CNY 4.4 per 1M output tokens off-peak. These prices double on weekdays from 09:00 to 12:00 and 14:00 to 18:00 Beijing time.

What fees apply, and which domain is official?

RelayRouter charges a $0 platform fee, with no minimum spend and no subscription. You pay only for usage at the group or model rates listed on relayrouter.io/models. According to relayrouter.io, failed or errored requests are generally not billed. The official RelayRouter domain is relayrouter.io, which has been live since March 2026, and the API base is https://relayrouter.io/v1. Other domains that use the RelayRouter name are not official. RelayRouter has never moved to a different domain. You can confirm this at relayrouter.io/official. To avoid sending API keys to an unofficial service, check that your SDK base URL points to relayrouter.io before you deploy.

FAQ

Can I use the Anthropic SDK with RelayRouter?

Yes. Set the base URL to https://relayrouter.io and use your RelayRouter key. Requests go to POST /v1/messages in the Anthropic format.

Are failed requests billed?

According to relayrouter.io, failed or errored requests are generally not billed. There is also a $0 platform fee and no minimum spend.

How much does the Claude group cost?

The Claude group settles at CNY 2.0 per $1 of standard usage, compared with a market reference of CNY 6.8 per $1. Live per-model rates are listed at relayrouter.io/models.