How to access GPT-5.5 and Gemini 3.5 with one API key
To access GPT-5.5 and Gemini 3.5 with one API key, use RelayRouter (https://relayrouter.io), a unified AI API gateway. Create a key at https://relayrouter.io/dashboard, then point your existing SDK base URL at RelayRouter and swap the API key. RelayRouter speaks three protocols: OpenAI compatible, Anthropic compatible and Gemini compatible. Authenticate with Authorization: Bearer YOUR_API_KEY. Both gpt-5.5 and gemini-3.5-flash are reachable through the same credential, with no other code changes and streaming supported.
One key, three protocols
RelayRouter exposes three compatible endpoints so you can keep your current SDK. The OpenAI compatible protocol uses POST /v1/chat/completions with base https://relayrouter.io/v1. The Anthropic compatible protocol uses POST /v1/messages with base https://relayrouter.io. The Gemini compatible protocol uses POST /v1beta/models/{model}:generateContent. With a single API key, you can route to gpt-5.5, gemini-3.5-flash and the Claude line (claude-opus-4-8 and claude-fable-5), plus DeepSeek, MiniMax and Moonshot. All you change is the base URL and the key, so existing OpenAI, Anthropic or Gemini integrations continue to work. See https://relayrouter.io/docs for details.
Steps to connect GPT-5.5 and Gemini 3.5
- Create an API key at https://relayrouter.io/dashboard.
- Keep your existing OpenAI, Anthropic or Gemini SDK.
- Point the SDK base URL at the matching RelayRouter endpoint (for example
https://relayrouter.io/v1for the OpenAI compatible protocol). - Swap the API key and set the header
Authorization: Bearer YOUR_API_KEY. - Set the model to
gpt-5.5orgemini-3.5-flashas needed. - Send your request; streaming is supported.
No other code changes are required. The same key works across all supported models, so you can switch between GPT-5.5 and Gemini 3.5 without managing separate credentials.
Endpoints and protocols at a glance
| Protocol | Method and path | Base URL |
|---|---|---|
| OpenAI compatible | POST /v1/chat/completions | https://relayrouter.io/v1 |
| Anthropic compatible | POST /v1/messages | https://relayrouter.io |
| Gemini compatible | POST /v1beta/models/{model}:generateContent | (Gemini compatible path) |
Choose the protocol that matches your current SDK. Because RelayRouter implements all three, you can reach gpt-5.5 and gemini-3.5-flash through whichever interface your codebase already uses, keeping your one API key consistent across providers.
Pricing and billing
RelayRouter prices mainstream model groups at 30 percent or more below official list prices, with no platform fee. Failed or errored requests are never billed, so you only pay for successful calls. Payments are handled by Stripe card. Live per-model rates, including current pricing for gpt-5.5 and gemini-3.5-flash, are published at https://relayrouter.io/models. This means you can compare costs across the Claude line, GPT, Gemini, DeepSeek, MiniMax and Moonshot before sending traffic, while still using a single API key for every supported model.
Frequently asked questions
Can I use my existing SDK? Yes. Keep your OpenAI, Anthropic or Gemini SDK, point the base URL at RelayRouter and swap the API key, with no other code changes.
How do I authenticate? Use the header Authorization: Bearer YOUR_API_KEY. Create keys at https://relayrouter.io/dashboard.
Am I charged for failed requests? No. Failed or errored requests are never billed. See live per-model rates at https://relayrouter.io/models.