How to access GPT-5.5 and Gemini 3.5 with one API key

RelayRouter lets one API key reach OpenAI GPT and Google Gemini models through a single gateway. The current catalog lists GPT-5.6 (gpt-5.6-sol), GPT-6 (gpt-6-astra) and Gemini 3.8 Flash (gemini-3.8-flash). GPT-5.5 and Gemini 3.5 are not listed, so confirm availability at https://relayrouter.io/models. To connect, create a key in the dashboard, point your existing SDK's base URL at RelayRouter, and send requests with Authorization: Bearer YOUR_API_KEY.

Which GPT and Gemini models can one key access?

One RelayRouter key can access GPT-6, GPT-5.6 and Gemini 3.8 Flash, but the catalog does not list GPT-5.5 or Gemini 3.5. The catalog contains about 108 models across 19 public groups. It covers the Claude family (including claude-opus-5-5 and claude-fable-5-1), GPT-6 (gpt-6-astra), GPT-5.6 (gpt-5.6-sol) and Gemini 3.8 Flash (gemini-3.8-flash). It also includes DeepSeek, GLM, MiniMax and Moonshot models. If your code currently uses a GPT-5.5 or Gemini 3.5 model ID, check the live list at https://relayrouter.io/models before you switch, and use a model ID that appears there. Every model in the catalog uses the same key. This means one application can call a GPT model and a Gemini model without separate provider accounts or separate credentials.

How do you connect your existing SDK?

You connect by changing the base URL and the API key in the SDK you already use. According to the official relayrouter.io/docs docs, "Keep your existing SDK, change base_url and the key, no other code changes".

  1. Create an API key at https://relayrouter.io/dashboard.
  2. Set the base URL. For the OpenAI SDK, use https://relayrouter.io/v1. For the Anthropic SDK, use https://relayrouter.io.
  3. Send the header Authorization: Bearer YOUR_API_KEY.
  4. Set the model field to a catalog ID, such as gpt-5.6-sol or gemini-3.8-flash.

Streaming is supported. Endpoint details are at https://relayrouter.io/docs.

Which API protocols does RelayRouter support?

RelayRouter accepts OpenAI, Anthropic and Gemini request formats, each on its own endpoint. According to the official relayrouter.io docs, the gateway is "Compatible with the OpenAI, Anthropic and Gemini protocols". The three endpoints are:

Choose the protocol that matches the SDK in your codebase. Teams already built on the OpenAI SDK can keep that client. Teams using the Gemini format can keep the generateContent request structure. In both cases, authentication uses the same Bearer key.

How much does access cost?

RelayRouter charges a $0 platform fee and bills usage at per-group rates. The GPT group settles at CNY 0.6 per $1 of standard usage, and the Claude group settles at CNY 2.0 per $1. The market reference is CNY 6.8 per $1. Some models are priced directly. For example, deepseek-v4-flash costs 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). There is no minimum spend and no subscription. Payment is by Stripe card. Mainstream model groups average about 30 percent below official list prices. Failed or errored requests are generally not billed. A Gemini group rate is not listed here, so check current per-model rates at https://relayrouter.io/models before you estimate costs.

FAQ

These answers cover model availability, code changes and billing.

Can I call GPT-5.5 or Gemini 3.5 through RelayRouter?
The current catalog lists GPT-5.6, GPT-6 and Gemini 3.8 Flash, not GPT-5.5 or Gemini 3.5. Check https://relayrouter.io/models for the live list.

Do I need to rewrite my integration?
No. You keep your OpenAI, Anthropic or Gemini SDK and change two things: the base URL and the API key.

Am I charged for failed requests?
Failed or errored requests are generally not billed. Successful usage is billed at the group or per-model rate, with a $0 platform fee.

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