Gemini

Route your Google Gemini requests through Metrion using the OpenAI-compatible SDK — with a one-line change.

Use Metrion as a proxy for Google Gemini. Because Metrion connects to Gemini’s OpenAI-compatible endpoint, you can use the standard OpenAI SDK — only the baseURL changes.

Metrion routes Gemini requests through Google’s OpenAI-compatible API endpoint (generativelanguage.googleapis.com/v1beta/openai/chat/completions). You use the OpenAI SDK, and Metrion handles the translation.

Prerequisites

• A Metrion account with your sk-metrion-xxx token (find it on the Integrate page)
• A Google Gemini API key saved in Metrion’s Integrate page

Setup

1. Install the OpenAI SDK
2. TypeScript

   npm install openai
   

   Python

   pip install openai
   
3. Configure the client
4. Set baseURL to Metrion’s Gemini proxy and pass your sk-metrion-xxx token as apiKey. Metrion injects your Gemini key and forwards the request to Google’s API.
5. TypeScript

   import OpenAI from 'openai'
   
   const client = new OpenAI({
     apiKey: 'sk-metrion-xxx',       // your Metrion token
     baseURL: 'https://www.metrion.dev/api/proxy/gemini',
   })
   

   Python

   from openai import OpenAI
   
   client = OpenAI(
       api_key="sk-metrion-xxx",     # your Metrion token
       base_url="https://www.metrion.dev/api/proxy/gemini",
   )
   
6. Send a request
7. TypeScript

   import OpenAI from 'openai'
   
   const client = new OpenAI({
     apiKey: 'sk-metrion-xxx',
     baseURL: 'https://www.metrion.dev/api/proxy/gemini',
   })
   
   const message = await client.chat.completions.create({
     model: 'gemini-2.0-flash',
     max_tokens: 1024,
     messages: [{ role: 'user', content: 'Hello, world!' }],
   })
   
   console.log(message.choices[0].message.content)
   

   Python

   from openai import OpenAI
   
   client = OpenAI(
       api_key="sk-metrion-xxx",
       base_url="https://www.metrion.dev/api/proxy/gemini",
   )
   
   message = client.chat.completions.create(
       model="gemini-2.0-flash",
       max_tokens=1024,
       messages=[{"role": "user", "content": "Hello, world!"}],
   )
   
   print(message.choices[0].message.content)
   

Direct HTTP

curl https://www.metrion.dev/api/proxy/gemini/v1/chat/completions \
  -H 'Authorization: Bearer sk-metrion-xxx' \
  -H 'content-type: application/json' \
  -d '{
    "model": "gemini-2.0-flash",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Hello, world!"}]
  }'

Supported models

Model ID	Notes
gemini-2.0-flash	Fast, multimodal, low cost
gemini-2.5-pro	Most capable Gemini model
gemini-2.5-flash	Fast and cost-efficient
gemini-1.5-pro	Long context (1M tokens)
gemini-1.5-flash	Fast and lightweight

Pass-through mode

To use your own Gemini key without storing it in Metrion, pass it in Authorization: Bearer and identify your Metrion account with the x-metrion-token header:

TypeScript

import OpenAI from 'openai'

const client = new OpenAI({
  apiKey: process.env.GEMINI_API_KEY,      // your Gemini key directly
  baseURL: 'https://www.metrion.dev/api/proxy/gemini',
  defaultHeaders: {
    'x-metrion-token': 'sk-metrion-xxx',   // identifies your Metrion account
  },
})

In pass-through mode, your Gemini key is forwarded directly to Google’s API and is never stored by Metrion.

Track requests by user or service

Add the optional x-metrion-user header to tag individual requests. These labels appear in your Metrion logs and dashboards.

Use x-metrion-user to break down costs by team member, bot, or application — for example "x-metrion-user": "pipeline-rag" or "x-metrion-user": "user-12".

TypeScript

const client = new OpenAI({
  apiKey: 'sk-metrion-xxx',
  baseURL: 'https://www.metrion.dev/api/proxy/gemini',
  defaultHeaders: {
    'x-metrion-user': 'user-12',
  },
})