Përputhshmëria me OpenAI

Gemini models are accessible using the OpenAI libraries (Python and TypeScript / Javascript) along with the REST API, by updating three lines of code and using your Gemini API key . If you aren't already using the OpenAI libraries, we recommend that you call the Gemini API directly .

Python 

from openai import OpenAI

client = OpenAI(
    api_key="GEMINI_API_KEY",
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

response = client.chat.completions.create(
    model="gemini-3-flash-preview",
    messages=[
        {   "role": "system",
            "content": "You are a helpful assistant."
        },
        {
            "role": "user",
            "content": "Explain to me how AI works"
        }
    ]
)

print(response.choices[0].message)

JavaScript 

import OpenAI from "openai";

const openai = new OpenAI({
    apiKey: "GEMINI_API_KEY",
    baseURL: "https://generativelanguage.googleapis.com/v1beta/openai/"
});

const response = await openai.chat.completions.create({
    model: "gemini-3-flash-preview",
    messages: [
        {   role: "system",
            content: "You are a helpful assistant." 
        },
        {
            role: "user",
            content: "Explain to me how AI works",
        },
    ],
});

console.log(response.choices[0].message);

PUSHTIM 

curl "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $GEMINI_API_KEY" \
  -d '{
    "model": "gemini-3-flash-preview",
    "messages": [
      {
        "role": "user",
        "content": "Explain to me how AI works"
      }
    ]
  }'

Çfarë ndryshoi? Vetëm tre rreshta!

  • api_key="GEMINI_API_KEY" : Zëvendësoni " GEMINI_API_KEY " me çelësin tuaj aktual Gemini API, të cilin mund ta merrni në Google AI Studio .

  • base_url="https://generativelanguage.googleapis.com/v1beta/openai/" : Kjo i tregon bibliotekës OpenAI të dërgojë kërkesa te pika fundore e API-t Gemini në vend të URL-së së parazgjedhur.

  • model="gemini-3-flash-preview" : Zgjidhni një model të pajtueshëm Gemini

Të menduarit

Gemini models are trained to think through complex problems, leading to significantly improved reasoning. The Gemini API comes with thinking parameters which give fine grain control over how much the model will think.

Modele të ndryshme Gemini kanë konfigurime të ndryshme arsyetimi, mund të shihni se si ato përputhen me përpjekjet e arsyetimit të OpenAI si më poshtë:

reasoning_effort (OpenAI) thinking_level (Gemini 3.1 Pro) thinking_level (Gemini 3.1 Flash-Lite) thinking_level (Binjakët 3 Flash) thinking_budget (Binjakët 2.5)
minimal low minimal minimal 1,024
low low low low 1,024
medium medium medium medium 8,192
high high high high 24,576

Nëse nuk specifikohet reasoning_effort , Gemini përdor nivelin ose buxhetin e parazgjedhur të modelit.

Nëse doni të çaktivizoni të menduarit, mund ta vendosni reasoning_effort në "none" për modelet 2.5. Arsyetimi nuk mund të çaktivizohet për modelet Gemini 2.5 Pro ose 3.

Python 

from openai import OpenAI

client = OpenAI(
    api_key="GEMINI_API_KEY",
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

response = client.chat.completions.create(
    model="gemini-3-flash-preview",
    reasoning_effort="low",
    messages=[
        {   "role": "system",
            "content": "You are a helpful assistant."
        },
        {
            "role": "user",
            "content": "Explain to me how AI works"
        }
    ]
)

print(response.choices[0].message)

JavaScript 

import OpenAI from "openai";

const openai = new OpenAI({
    apiKey: "GEMINI_API_KEY",
    baseURL: "https://generativelanguage.googleapis.com/v1beta/openai/"
});

const response = await openai.chat.completions.create({
    model: "gemini-3-flash-preview",
    reasoning_effort: "low",
    messages: [
        {   role: "system",
            content: "You are a helpful assistant." 
        },
        {
            role: "user",
            content: "Explain to me how AI works",
        },
    ],
});

console.log(response.choices[0].message);

PUSHTIM 

curl "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $GEMINI_API_KEY" \
  -d '{
    "model": "gemini-3-flash-preview",
    "reasoning_effort": "low",
    "messages": [
      {
        "role": "user",
        "content": "Explain to me how AI works"
      }
    ]
  }'

Modelet e të menduarit Gemini prodhojnë gjithashtu përmbledhje mendimesh . Mund të përdorni fushën extra_body për të përfshirë fushat Gemini në kërkesën tuaj.

Vini re se reasoning_effort dhe thinking_level / thinking_budget mbivendosen me njëra-tjetrën, kështu që ato nuk mund të përdoren në të njëjtën kohë.

Python 

from openai import OpenAI

client = OpenAI(
    api_key="GEMINI_API_KEY",
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

response = client.chat.completions.create(
    model="gemini-3-flash-preview",
    messages=[{"role": "user", "content": "Explain to me how AI works"}],
    extra_body={
      'extra_body': {
        "google": {
          "thinking_config": {
            "thinking_level": "low",
            "include_thoughts": True
          }
        }
      }
    }
)

print(response.choices[0].message)

JavaScript 

import OpenAI from "openai";

const openai = new OpenAI({
    apiKey: "GEMINI_API_KEY",
    baseURL: "https://generativelanguage.googleapis.com/v1beta/openai/"
});

const response = await openai.chat.completions.create({
    model: "gemini-3-flash-preview",
    messages: [{role: "user", content: "Explain to me how AI works",}],
    extra_body: {
      "google": {
        "thinking_config": {
          "thinking_level": "low",
          "include_thoughts": true
        }
      }
    }
});

console.log(response.choices[0].message);

PUSHTIM 

curl "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer GEMINI_API_KEY" \
  -d '{
      "model": "gemini-3-flash-preview",
        "messages": [{"role": "user", "content": "Explain to me how AI works"}],
        "extra_body": {
          "google": {
            "thinking_config": {
              "thinking_level": "low",
              "include_thoughts": true
            }
          }
        }
      }'

Gemini 3 mbështet përputhshmërinë me OpenAI për nënshkrimet e mendimeve në API-të e përfundimit të bisedave. Mund ta gjeni shembullin e plotë në faqen e nënshkrimeve të mendimeve .

Transmetim

API-ja Gemini mbështet përgjigjet e transmetimit .

Python 

from openai import OpenAI

client = OpenAI(
    api_key="GEMINI_API_KEY",
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

response = client.chat.completions.create(
  model="gemini-3-flash-preview",
  messages=[
    {
        "role": "system",
        "content": "You are a helpful assistant."
    },
    {   "role": "user",
        "content": "Hello!"
    }
  ],
  stream=True
)

for chunk in response:
    print(chunk.choices[0].delta)

JavaScript 

import OpenAI from "openai";

const openai = new OpenAI({
    apiKey: "GEMINI_API_KEY",
    baseURL: "https://generativelanguage.googleapis.com/v1beta/openai/"
});

async function main() {
  const completion = await openai.chat.completions.create({
    model: "gemini-3-flash-preview",
    messages: [
      {
          "role": "system",
          "content": "You are a helpful assistant."
      },
      {
          "role": "user",
          "content": "Hello!"
      }
    ],
    stream: true,
  });

  for await (const chunk of completion) {
    console.log(chunk.choices[0].delta.content);
  }
}

main();

PUSHTIM 

curl "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer GEMINI_API_KEY" \
  -d '{
      "model": "gemini-3-flash-preview",
      "messages": [
          {"role": "user", "content": "Explain to me how AI works"}
      ],
      "stream": true
    }'

Thirrja e funksionit

Thirrja e funksioneve e bën më të lehtë për ju marrjen e rezultateve të të dhënave të strukturuara nga modelet gjeneruese dhe mbështetet në Gemini API .

Python 

from openai import OpenAI

client = OpenAI(
    api_key="GEMINI_API_KEY",
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

tools = [
  {
    "type": "function",
    "function": {
      "name": "get_weather",
      "description": "Get the weather in a given location",
      "parameters": {
        "type": "object",
        "properties": {
          "location": {
            "type": "string",
            "description": "The city and state, e.g. Chicago, IL",
          },
          "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
        },
        "required": ["location"],
      },
    }
  }
]

messages = [{"role": "user", "content": "What's the weather like in Chicago today?"}]
response = client.chat.completions.create(
  model="gemini-3-flash-preview",
  messages=messages,
  tools=tools,
  tool_choice="auto"
)

print(response)

JavaScript 

import OpenAI from "openai";

const openai = new OpenAI({
    apiKey: "GEMINI_API_KEY",
    baseURL: "https://generativelanguage.googleapis.com/v1beta/openai/"
});

async function main() {
  const messages = [{"role": "user", "content": "What's the weather like in Chicago today?"}];
  const tools = [
      {
        "type": "function",
        "function": {
          "name": "get_weather",
          "description": "Get the weather in a given location",
          "parameters": {
            "type": "object",
            "properties": {
              "location": {
                "type": "string",
                "description": "The city and state, e.g. Chicago, IL",
              },
              "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
            },
            "required": ["location"],
          },
        }
      }
  ];

  const response = await openai.chat.completions.create({
    model: "gemini-3-flash-preview",
    messages: messages,
    tools: tools,
    tool_choice: "auto",
  });

  console.log(response);
}

main();

PUSHTIM 

curl "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer GEMINI_API_KEY" \
-d '{
  "model": "gemini-3-flash-preview",
  "messages": [
    {
      "role": "user",
      "content": "What'\''s the weather like in Chicago today?"
    }
  ],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Get the current weather in a given location",
        "parameters": {
          "type": "object",
          "properties": {
            "location": {
              "type": "string",
              "description": "The city and state, e.g. Chicago, IL"
            },
            "unit": {
              "type": "string",
              "enum": ["celsius", "fahrenheit"]
            }
          },
          "required": ["location"]
        }
      }
    }
  ],
  "tool_choice": "auto"
}'

Kuptimi i imazhit

Modelet Gemini janë multimodale në thelb dhe ofrojnë performancën më të mirë në klasën e tyre në shumë detyra të zakonshme të shikimit .

Python 

import base64
from openai import OpenAI

client = OpenAI(
    api_key="GEMINI_API_KEY",
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

# Function to encode the image
def encode_image(image_path):
  with open(image_path, "rb") as image_file:
    return base64.b64encode(image_file.read()).decode('utf-8')

# Getting the base64 string
base64_image = encode_image("Path/to/agi/image.jpeg")

response = client.chat.completions.create(
  model="gemini-3-flash-preview",
  messages=[
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "What is in this image?",
        },
        {
          "type": "image_url",
          "image_url": {
            "url":  f"data:image/jpeg;base64,{base64_image}"
          },
        },
      ],
    }
  ],
)

print(response.choices[0])

JavaScript 

import OpenAI from "openai";
import fs from 'fs/promises';

const openai = new OpenAI({
  apiKey: "GEMINI_API_KEY",
  baseURL: "https://generativelanguage.googleapis.com/v1beta/openai/"
});

async function encodeImage(imagePath) {
  try {
    const imageBuffer = await fs.readFile(imagePath);
    return imageBuffer.toString('base64');
  } catch (error) {
    console.error("Error encoding image:", error);
    return null;
  }
}

async function main() {
  const imagePath = "Path/to/agi/image.jpeg";
  const base64Image = await encodeImage(imagePath);

  const messages = [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "What is in this image?",
        },
        {
          "type": "image_url",
          "image_url": {
            "url": `data:image/jpeg;base64,${base64Image}`
          },
        },
      ],
    }
  ];

  try {
    const response = await openai.chat.completions.create({
      model: "gemini-3-flash-preview",
      messages: messages,
    });

    console.log(response.choices[0]);
  } catch (error) {
    console.error("Error calling Gemini API:", error);
  }
}

main();

PUSHTIM 

bash -c '
  base64_image=$(base64 -i "Path/to/agi/image.jpeg");
  curl "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions" \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer GEMINI_API_KEY" \
    -d "{
      \"model\": \"gemini-3-flash-preview\",
      \"messages\": [
        {
          \"role\": \"user\",
          \"content\": [
            { \"type\": \"text\", \"text\": \"What is in this image?\" },
            {
              \"type\": \"image_url\",
              \"image_url\": { \"url\": \"data:image/jpeg;base64,${base64_image}\" }
            }
          ]
        }
      ]
    }"
'

Gjeneroni një imazh

Generate an image using gemini-2.5-flash-image or gemini-3-pro-image-preview . Supported parameters include prompt , model , n , size , and response_format . Any other parameters not listed here or in the extra_body section will be silently ignored by the compatibility layer.

Python 

import base64
from openai import OpenAI
from PIL import Image
from io import BytesIO

client = OpenAI(
    api_key="GEMINI_API_KEY",
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/",
)

response = client.images.generate(
    model="gemini-2.5-flash-image",
    prompt="a portrait of a sheepadoodle wearing a cape",
    response_format='b64_json',
    n=1,
)

for image_data in response.data:
  image = Image.open(BytesIO(base64.b64decode(image_data.b64_json)))
  image.show()

JavaScript 

import OpenAI from "openai";

const openai = new OpenAI({
  apiKey: "GEMINI_API_KEY",
  baseURL: "https://generativelanguage.googleapis.com/v1beta/openai/",
});

async function main() {
  const image = await openai.images.generate(
    {
      model: "gemini-2.5-flash-image",
      prompt: "a portrait of a sheepadoodle wearing a cape",
      response_format: "b64_json",
      n: 1,
    }
  );

  console.log(image.data);
}

main();

PUSHTIM 

curl "https://generativelanguage.googleapis.com/v1beta/openai/images/generations" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer GEMINI_API_KEY" \
  -d '{
        "model": "gemini-2.5-flash-image",
        "prompt": "a portrait of a sheepadoodle wearing a cape",
        "response_format": "b64_json",
        "n": 1,
      }'

Gjenero një video

Generate a video using veo-3.1-generate-preview via the Sora-compatible /v1/videos endpoint. Supported top-level parameters are prompt and model . Additional parameters like duration_seconds , image , and aspect_ratio must be passed with extra_body . See the extra_body section for all available parameters.

Gjenerimi i videos është një operacion afatgjatë që kthen një ID operacioni që mund ta anketoni për përfundim.

Python 

from openai import OpenAI

client = OpenAI(
    api_key="GEMINI_API_KEY",
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

# Returns a Long Running Operation (status: processing)
response = client.videos.create(
    model="veo-3.1-generate-preview",
    prompt="A cinematic drone shot of a waterfall",
)

print(f"Operation ID: {response.id}")
print(f"Status: {response.status}")

JavaScript 

import OpenAI from "openai";

const openai = new OpenAI({
    apiKey: "GEMINI_API_KEY",
    baseURL: "https://generativelanguage.googleapis.com/v1beta/openai/"
});

async function main() {
    // Returns a Long Running Operation (status: processing)
    const response = await openai.videos.create({
        model: "veo-3.1-generate-preview",
        prompt: "A cinematic drone shot of a waterfall",
    });

    console.log(`Operation ID: ${response.id}`);
    console.log(`Status: ${response.status}`);
}

main();

PUSHTIM 

curl "https://generativelanguage.googleapis.com/v1beta/openai/videos" \
  -H "Authorization: Bearer $GEMINI_API_KEY" \
  -F "model=veo-3.1-generate-preview" \
  -F "prompt=A cinematic drone shot of a waterfall"

Kontrolloni statusin e videos

Gjenerimi i videos është asinkron. Përdorni GET /v1/videos/{id} për të anketuar statusin dhe për të marrë URL-në përfundimtare të videos kur të përfundojë:

Python 

import time
from openai import OpenAI

client = OpenAI(
    api_key="GEMINI_API_KEY",
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

# Poll until video is ready
video_id = response.id  # From the create call
while True:
    video = client.videos.retrieve(video_id)
    if video.status == "completed":
        print(f"Video URL: {video.url}")
        break
    elif video.status == "failed":
        print(f"Generation failed: {video.error}")
        break
    print(f"Status: {video.status}. Waiting...")
    time.sleep(10)

JavaScript 

import OpenAI from "openai";

const openai = new OpenAI({
    apiKey: "GEMINI_API_KEY",
    baseURL: "https://generativelanguage.googleapis.com/v1beta/openai/"
});

async function main() {
    // Poll until video is ready
    const videoId = response.id;  // From the create call
    while (true) {
        const video = await openai.videos.retrieve(videoId);
        if (video.status === "completed") {
            console.log(`Video URL: ${video.url}`);
            break;
        } else if (video.status === "failed") {
            console.log(`Generation failed: ${video.error}`);
            break;
        }
        console.log(`Status: ${video.status}. Waiting...`);
        await new Promise(resolve => setTimeout(resolve, 10000));
    }
}

main();

PUSHTIM 

curl "https://generativelanguage.googleapis.com/v1beta/openai/videos/VIDEO_ID" \
  -H "Authorization: Bearer $GEMINI_API_KEY"

Kuptimi i audios

Analizoni hyrjen audio:

Python 

import base64
from openai import OpenAI

client = OpenAI(
    api_key="GEMINI_API_KEY",
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

with open("/path/to/your/audio/file.wav", "rb") as audio_file:
  base64_audio = base64.b64encode(audio_file.read()).decode('utf-8')

response = client.chat.completions.create(
    model="gemini-3-flash-preview",
    messages=[
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "Transcribe this audio",
        },
        {
              "type": "input_audio",
              "input_audio": {
                "data": base64_audio,
                "format": "wav"
          }
        }
      ],
    }
  ],
)

print(response.choices[0].message.content)

JavaScript 

import fs from "fs";
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "GEMINI_API_KEY",
  baseURL: "https://generativelanguage.googleapis.com/v1beta/openai/",
});

const audioFile = fs.readFileSync("/path/to/your/audio/file.wav");
const base64Audio = Buffer.from(audioFile).toString("base64");

async function main() {
  const response = await client.chat.completions.create({
    model: "gemini-3-flash-preview",
    messages: [
      {
        role: "user",
        content: [
          {
            type: "text",
            text: "Transcribe this audio",
          },
          {
            type: "input_audio",
            input_audio: {
              data: base64Audio,
              format: "wav",
            },
          },
        ],
      },
    ],
  });

  console.log(response.choices[0].message.content);
}

main();

PUSHTIM

bash -c '
  base64_audio=$(base64 -i "/path/to/your/audio/file.wav");
  curl "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions" \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer GEMINI_API_KEY" \
    -d "{
      \"model\": \"gemini-3-flash-preview\",
      \"messages\": [
        {
          \"role\": \"user\",
          \"content\": [
            { \"type\": \"text\", \"text\": \"Transcribe this audio file.\" },
            {
              \"type\": \"input_audio\",
              \"input_audio\": {
                \"data\": \"${base64_audio}\",
                \"format\": \"wav\"
              }
            }
          ]
        }
      ]
    }"
'

Prodhim i strukturuar

Modelet Gemini mund të nxjerrin objekte JSON në çdo strukturë që përcaktoni .

Python 

from pydantic import BaseModel
from openai import OpenAI

client = OpenAI(
    api_key="GEMINI_API_KEY",
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

class CalendarEvent(BaseModel):
    name: str
    date: str
    participants: list[str]

completion = client.beta.chat.completions.parse(
    model="gemini-3-flash-preview",
    messages=[
        {"role": "system", "content": "Extract the event information."},
        {"role": "user", "content": "John and Susan are going to an AI conference on Friday."},
    ],
    response_format=CalendarEvent,
)

print(completion.choices[0].message.parsed)

JavaScript 

import OpenAI from "openai";
import { zodResponseFormat } from "openai/helpers/zod";
import { z } from "zod";

const openai = new OpenAI({
    apiKey: "GEMINI_API_KEY",
    baseURL: "https://generativelanguage.googleapis.com/v1beta/openai"
});

const CalendarEvent = z.object({
  name: z.string(),
  date: z.string(),
  participants: z.array(z.string()),
});

const completion = await openai.chat.completions.parse({
  model: "gemini-3-flash-preview",
  messages: [
    { role: "system", content: "Extract the event information." },
    { role: "user", content: "John and Susan are going to an AI conference on Friday" },
  ],
  response_format: zodResponseFormat(CalendarEvent, "event"),
});

const event = completion.choices[0].message.parsed;
console.log(event);

Vendosje

Text embeddings measure the relatedness of text strings and can be generated using the Gemini API . You can use gemini-embedding-2-preview for multimodal embeddings or gemini-embedding-001 for text-only embeddings.

Python 

from openai import OpenAI

client = OpenAI(
    api_key="GEMINI_API_KEY",
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

response = client.embeddings.create(
    input="Your text string goes here",
    model="gemini-embedding-2-preview"
)

print(response.data[0].embedding)

JavaScript 

import OpenAI from "openai";

const openai = new OpenAI({
    apiKey: "GEMINI_API_KEY",
    baseURL: "https://generativelanguage.googleapis.com/v1beta/openai/"
});

async function main() {
  const embedding = await openai.embeddings.create({
    model: "gemini-embedding-2-preview",
    input: "Your text string goes here",
  });

  console.log(embedding);
}

main();

PUSHTIM 

curl "https://generativelanguage.googleapis.com/v1beta/openai/embeddings" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer GEMINI_API_KEY" \
-d '{
    "input": "Your text string goes here",
    "model": "gemini-embedding-2-preview"
  }'

API-ja e grupeve

Mund të krijoni punë në grupe , t'i dorëzoni ato dhe të kontrolloni statusin e tyre duke përdorur bibliotekën OpenAI.

Do të duhet ta përgatitni skedarin JSONL në formatin e hyrjes OpenAI. Për shembull: 

{"custom_id": "request-1", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "gemini-3-flash-preview", "messages": [{"role": "user", "content": "Tell me a one-sentence joke."}]}}
{"custom_id": "request-2", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "gemini-3-flash-preview", "messages": [{"role": "user", "content": "Why is the sky blue?"}]}}

Pajtueshmëria me OpenAI për Batch mbështet krijimin e një grupi, monitorimin e statusit të punës dhe shikimin e rezultateve të grupit.

Compatibility for upload and download is currently not supported. Instead, the following example uses the genai client for uploading and downloading files , the same as when using the Gemini Batch API .

Python 

from openai import OpenAI

# Regular genai client for uploads & downloads
from google import genai
client = genai.Client()

openai_client = OpenAI(
    api_key="GEMINI_API_KEY",
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

# Upload the JSONL file in OpenAI input format, using regular genai SDK
uploaded_file = client.files.upload(
    file='my-batch-requests.jsonl',
    config=types.UploadFileConfig(display_name='my-batch-requests', mime_type='jsonl')
)

# Create batch
batch = openai_client.batches.create(
    input_file_id=batch_input_file_id,
    endpoint="/v1/chat/completions",
    completion_window="24h"
)

# Wait for batch to finish (up to 24h)
while True:
    batch = client.batches.retrieve(batch.id)
    if batch.status in ('completed', 'failed', 'cancelled', 'expired'):
        break
    print(f"Batch not finished. Current state: {batch.status}. Waiting 30 seconds...")
    time.sleep(30)
print(f"Batch finished: {batch}")

# Download results in OpenAI output format, using regular genai SDK
file_content = genai_client.files.download(file=batch.output_file_id).decode('utf-8')

# See batch_output JSONL in OpenAI output format
for line in file_content.splitlines():
    print(line)

The OpenAI SDK also supports generating embeddings with the Batch API . To do so, switch out the create method's endpoint field for an embeddings endpoint, as well as the url and model keys in the JSONL file: 

# JSONL file using embeddings model and endpoint
# {"custom_id": "request-1", "method": "POST", "url": "/v1/embeddings", "body": {"model": "ggemini-embedding-001", "messages": [{"role": "user", "content": "Tell me a one-sentence joke."}]}}
# {"custom_id": "request-2", "method": "POST", "url": "/v1/embeddings", "body": {"model": "gemini-embedding-001", "messages": [{"role": "user", "content": "Why is the sky blue?"}]}}

# ...

# Create batch step with embeddings endpoint
batch = openai_client.batches.create(
    input_file_id=batch_input_file_id,
    endpoint="/v1/embeddings",
    completion_window="24h"
)

Shihni seksionin e gjenerimit të ngulitjes në seri të librit të gatimit të përputhshmërisë OpenAI për një shembull të plotë.

Përfundimi Fleks dhe Prioritet

API-ja Gemini përputhet me parametrin service_tier të OpenAI në emër dhe logjikë, duke zbatuar kufizime dhe duke drejtuar me elegancë trafikun për nivelet e përfundimit Flex dhe Priority.

Python 

from openai import OpenAI

client = OpenAI(
  api_key="GEMINI_API_KEY",
  base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

completion = client.chat.completions.create(
  model="gemini-3-flash-preview",
  messages=[
    {"role": "user", "content": "Write a short poem about clouds."}
  ],
  service_tier="priority" # Or service_tier="flex"
)

print(completion)

Kur nuk është caktuar në mënyrë të qartë, service_tier vendoset si standard si parazgjedhje, ekuivalente me default për OpenAI. Mësoni më shumë rreth niveleve të përfundimit në dokumentacionin e Optimizimit .

Aktivizo veçoritë Gemini me extra_body

Ekzistojnë disa veçori të mbështetura nga Gemini që nuk janë të disponueshme në modelet OpenAI, por mund të aktivizohen duke përdorur fushën extra_body .

Parametri Lloji Pika e Fundit Përshkrimi
cached_content Tekst Bisedë Korespondon me memorjen e përgjithshme të përmbajtjes së Gemini.
thinking_config Objekti Bisedë Korespondon me ThinkingConfig të Gemini-t.
aspect_ratio Tekst Imazhe Raporti i aspektit të daljes (p.sh., "16:9" , "1:1" , "9:16" ).
generation_config Objekti Imazhe Objekti i konfigurimit të gjenerimit Gemini (p.sh., {"responseModalities": ["IMAGE"], "candidateCount": 2} ).
safety_settings Listë Imazhe Filtra të personalizuar të pragut të sigurisë (p.sh., [{"category": "HARM_CATEGORY_HATE_SPEECH", "threshold": "BLOCK_NONE"}] ).
tools Listë Imazhe Aktivizon tokëzimin (p.sh., [{"google_search": {}}] ). Vetëm për gemini-3-pro-image-preview .
aspect_ratio Tekst Video Dimensionet e videos dalëse ( 16:9 për horizont, 9:16 për portret). Hartat nga size nëse nuk specifikohen.
resolution Tekst Video Rezolucioni i daljes ( 720p , 1080p , 4K ). Shënim: 1080p dhe 4K aktivizojnë tubacionin e marrjes së mostrave shtesë.
duration_seconds Numër i plotë Video Gjatësia e gjenerimit (vlerat: 4 , 6 , 8 ). Duhet të jetë 8 kur përdoret reference_images , interpolim ose zgjerim.
frame_rate Tekst Video Shpejtësia e kuadrove për daljen e videos (p.sh., "24" ).
input_reference Tekst Video Të dhëna referuese për gjenerimin e videos.
extend_video_id Tekst Video ID-ja e një videoje ekzistuese që do të zgjerohet.
negative_prompt Tekst Video Artikuj që duhen përjashtuar (p.sh., "shaky camera" ).
seed Numër i plotë Video Numër i plotë për gjenerim determinist.
style Tekst Video Stil vizual (parazgjedhur cinematic , creative optimizuar për mediat sociale).
person_generation Tekst Video Kontrollon gjenerimin e njerëzve ( allow_adult , allow_all , dont_allow ).
reference_images Listë Video Deri në 3 imazhe për referencë stili/personazhi (asete base64).
image Tekst Video Imazh hyrës fillestar i koduar në Base64 për të kushtëzuar gjenerimin e videos.
last_frame Objekti Video Imazhi përfundimtar për interpolim (kërkon image si kornizë të parë).

Shembull duke përdorur extra_body

Ja një shembull i përdorimit të extra_body për të vendosur cached_content :

Python 

from openai import OpenAI

client = OpenAI(
    api_key=MY_API_KEY,
    base_url="https://generativelanguage.googleapis.com/v1beta/"
)

stream = client.chat.completions.create(
    model="gemini-3-flash-preview",
    n=1,
    messages=[
        {
            "role": "user",
            "content": "Summarize the video"
        }
    ],
    stream=True,
    stream_options={'include_usage': True},
    extra_body={
        'extra_body':
        {
            'google': {
              'cached_content': "cachedContents/0000aaaa1111bbbb2222cccc3333dddd4444eeee"
          }
        }
    }
)

for chunk in stream:
    print(chunk)
    print(chunk.usage.to_dict())

Listoni modelet

Merrni një listë të modeleve Gemini në dispozicion:

Python 

from openai import OpenAI

client = OpenAI(
  api_key="GEMINI_API_KEY",
  base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

models = client.models.list()
for model in models:
  print(model.id)

JavaScript 

import OpenAI from "openai";

const openai = new OpenAI({
  apiKey: "GEMINI_API_KEY",
  baseURL: "https://generativelanguage.googleapis.com/v1beta/openai/",
});

async function main() {
  const list = await openai.models.list();

  for await (const model of list) {
    console.log(model);
  }
}
main();

PUSHTIM 

curl https://generativelanguage.googleapis.com/v1beta/openai/models \
-H "Authorization: Bearer GEMINI_API_KEY"

Merrni një model

Merrni një model Gemini:

Python 

from openai import OpenAI

client = OpenAI(
  api_key="GEMINI_API_KEY",
  base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

model = client.models.retrieve("gemini-3-flash-preview")
print(model.id)

JavaScript 

import OpenAI from "openai";

const openai = new OpenAI({
  apiKey: "GEMINI_API_KEY",
  baseURL: "https://generativelanguage.googleapis.com/v1beta/openai/",
});

async function main() {
  const model = await openai.models.retrieve("gemini-3-flash-preview");
  console.log(model.id);
}

main();

PUSHTIM 

curl https://generativelanguage.googleapis.com/v1beta/openai/models/gemini-3-flash-preview \
-H "Authorization: Bearer GEMINI_API_KEY"

Kufizimet aktuale

Mbështetja për bibliotekat OpenAI është ende në versionin beta, ndërsa ne zgjerojmë mbështetjen për veçoritë.

Nëse keni pyetje në lidhje me parametrat e mbështetur, veçoritë e ardhshme ose hasni ndonjë problem gjatë fillimit me Gemini, bashkohuni me Forumin tonë të Zhvilluesve .

Çfarë vjen më pas

Provoni OpenAI Compatibility Colab tonë për të punuar me shembuj më të detajuar.