GeminiAI Compatibility with OpenAI
GeminiAI is a developer-friendly large language model. It boasts a beautiful interface, powerful features, and a generous daily free tier sufficient for everyday use.
However, it also has some drawbacks, such as the constant need for a VPN and incompatibility with the OpenAI SDK.
To address these issues and achieve OpenAI compatibility, I wrote a JavaScript code and deployed it on Cloudflare, binding it to my own domain. This allows me to use Gemini in mainland China without a VPN while remaining compatible with OpenAI. In any tool that uses OpenAI, you can simply replace the API address and secret key (SK).
Creating a Worker on Cloudflare
If you don't have a Cloudflare account, please register one (free). The registration address is: https://dash.cloudflare.com/ After logging in, remember to bind your own domain, otherwise, you won't be able to achieve proxy-free access.
After logging in, find Compute (Workers) in the left sidebar and click it, then click the Create button.
On the page that appears, click Create Worker.
Then click Deploy in the lower right corner. This completes the creation of the Worker.
Editing the Code
The following code is the key to achieving OpenAI compatibility. Please copy it and replace the default code generated in the Worker.
On the page where you just finished deploying, click Edit Code.
Delete all the code on the left, then copy the following code and paste it. Finally, click Deploy in the upper right corner.
Copy the following code
export default {
async fetch (request) {
if (request.method === "OPTIONS") {
return handleOPTIONS();
}
const errHandler = (err) => {
console.error(err);
return new Response(err.message, fixCors({ status: err.status ?? 500 }));
};
try {
const auth = request.headers.get("Authorization");
const apiKey = auth?.split(" ")[1];
const assert = (success) => {
if (!success) {
throw new HttpError("The specified HTTP method is not allowed for the requested resource", 400);
}
};
const { pathname } = new URL(request.url);
if(!pathname.endsWith("/chat/completions")){
return new Response("hello")
}
assert(request.method === "POST");
return handleCompletions(await request.json(), apiKey).catch(errHandler);
} catch (err) {
return errHandler(err);
}
}
};
class HttpError extends Error {
constructor(message, status) {
super(message);
this.name = this.constructor.name;
this.status = status;
}
}
const fixCors = ({ headers, status, statusText }) => {
headers = new Headers(headers);
headers.set("Access-Control-Allow-Origin", "*");
return { headers, status, statusText };
};
const handleOPTIONS = async () => {
return new Response(null, {
headers: {
"Access-Control-Allow-Origin": "*",
"Access-Control-Allow-Methods": "*",
"Access-Control-Allow-Headers": "*",
}
});
};
const BASE_URL = "https://generativelanguage.googleapis.com";
const API_VERSION = "v1beta";
// https://github.com/google-gemini/generative-ai-js/blob/cf223ff4a1ee5a2d944c53cddb8976136382bee6/src/requests/request.ts#L71
const API_CLIENT = "genai-js/0.21.0"; // npm view @google/generative-ai version
const makeHeaders = (apiKey, more) => ({
"x-goog-api-client": API_CLIENT,
...(apiKey && { "x-goog-api-key": apiKey }),
...more
});
const DEFAULT_MODEL = "gemini-2.0-flash-exp";
async function handleCompletions (req, apiKey) {
let model = DEFAULT_MODEL;
if(req.model.startsWith("gemini-")) {
model = req.model;
}
const TASK = "generateContent";
let url = `${BASE_URL}/${API_VERSION}/models/${model}:${TASK}`;
const response = await fetch(url, {
method: "POST",
headers: makeHeaders(apiKey, { "Content-Type": "application/json" }),
body: JSON.stringify(await transformRequest(req)), // try
});
let body = response.body;
if (response.ok) {
let id = generateChatcmplId();
body = await response.text();
body = processCompletionsResponse(JSON.parse(body), model, id);
}
return new Response(body, fixCors(response));
}
const harmCategory = [
"HARM_CATEGORY_HATE_SPEECH",
"HARM_CATEGORY_SEXUALLY_EXPLICIT",
"HARM_CATEGORY_DANGEROUS_CONTENT",
"HARM_CATEGORY_HARASSMENT",
"HARM_CATEGORY_CIVIC_INTEGRITY",
];
const safetySettings = harmCategory.map(category => ({
category,
threshold: "BLOCK_NONE",
}));
const fieldsMap = {
stop: "stopSequences",
n: "candidateCount",
max_tokens: "maxOutputTokens",
max_completion_tokens: "maxOutputTokens",
temperature: "temperature",
top_p: "topP",
top_k: "topK",
frequency_penalty: "frequencyPenalty",
presence_penalty: "presencePenalty",
};
const transformConfig = (req) => {
let cfg = {};
for (let key in req) {
const matchedKey = fieldsMap[key];
if (matchedKey) {
cfg[matchedKey] = req[key];
}
}
cfg.responseMimeType = "text/plain";
return cfg;
};
const transformMsg = async ({ role, content }) => {
const parts = [];
if (!Array.isArray(content)) {
parts.push({ text: content });
return { role, parts };
}
for (const item of content) {
switch (item.type) {
case "text":
parts.push({ text: item.text });
break;
case "input_audio":
parts.push({
inlineData: {
mimeType: "audio/" + item.input_audio.format,
data: item.input_audio.data,
}
});
break;
default:
throw new TypeError(`Unknown "content" item type: "${item.type}"`);
}
}
if (content.every(item => item.type === "image_url")) {
parts.push({ text: "" });
}
return { role, parts };
};
const transformMessages = async (messages) => {
if (!messages) { return; }
const contents = [];
let system_instruction;
for (const item of messages) {
if (item.role === "system") {
delete item.role;
system_instruction = await transformMsg(item);
} else {
item.role = item.role === "assistant" ? "model" : "user";
contents.push(await transformMsg(item));
}
}
if (system_instruction && contents.length === 0) {
contents.push({ role: "model", parts: { text: " " } });
}
return { system_instruction, contents };
};
const transformRequest = async (req) => ({
...await transformMessages(req.messages),
safetySettings,
generationConfig: transformConfig(req),
});
const generateChatcmplId = () => {
const characters = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789";
const randomChar = () => characters[Math.floor(Math.random() * characters.length)];
return "chatcmpl-" + Array.from({ length: 29 }, randomChar).join("");
};
const reasonsMap = {
"STOP": "stop",
"MAX_TOKENS": "length",
"SAFETY": "content_filter",
"RECITATION": "content_filter"
};
const SEP = "\n\n|>";
const transformCandidates = (key, cand) => ({
index: cand.index || 0,
[key]: {
role: "assistant",
content: cand.content?.parts.map(p => p.text).join(SEP) },
logprobs: null,
finish_reason: reasonsMap[cand.finishReason] || cand.finishReason,
});
const transformCandidatesMessage = transformCandidates.bind(null, "message");
const transformCandidatesDelta = transformCandidates.bind(null, "delta");
const transformUsage = (data) => ({
completion_tokens: data.candidatesTokenCount,
prompt_tokens: data.promptTokenCount,
total_tokens: data.totalTokenCount
});
const processCompletionsResponse = (data, model, id) => {
return JSON.stringify({
id,
choices: data.candidates.map(transformCandidatesMessage),
created: Math.floor(Date.now()/1000),
model,
object: "chat.completion",
usage: transformUsage(data.usageMetadata),
});
};Binding a Domain
After deployment, Cloudflare will provide a second-level subdomain, but this domain cannot be accessed normally in mainland China. Therefore, you need to bind your own domain to achieve proxy-free access.
After deployment, click Back on the left.
Then find Settings -- Domains & Routes and click Add.
As shown in the figure below, add the domain you have already hosted on Cloudflare.
Once completed, you can use this domain to access Gemini.
Using the OpenAI SDK to Access Gemini
from openai import OpenAI, APIConnectionError
model = OpenAI(api_key='Your Gemini API Key', base_url='https://yourcustomdomain.com')
response = model.chat.completions.create(
model='gemini-2.0-flash-exp',
messages=[
{
'role': 'user',
'content': 'Who are you?'},
]
)
print(response.choices[0])Returns:
Choice(finish_reason='stop', index=0, logprobs=None, message=ChatCompletionMessage(content='I am a large language model, trained by Google.\n', refusal=None, role='assistant', audio=None, function_call=None, tool_calls=None))Using in Other OpenAI-Compatible Tools
Find the location where you configure OpenAI information in the tool, change the API address to the custom domain you added in Cloudflare, change the SK to your Gemini API Key, and fill in gemini-2.0-flash-exp for the model.
Accessing Directly with Requests
If you don't use the OpenAI SDK, you can also access it directly using the requests library.
import requests
payload={
"model":"gemini-1.5-flash",
"messages":[{
"role":"user",
"content":[{"type":"text","text":"Who are you?"}]
}]
}
res=requests.post('https://xxxx.com/chat/completions',headers={"Authorization":"Bearer Your Gemini API Key","Content-Type":"application:/json"},json=payload)
print(res.json())Output:
Related Resources
- The source code is modified from the project PublicAffairs/openai-gemini
- GeminiAI Documentation