OpenAI-Kompatibilität

Gemini-Modelle sind über die OpenAI-Bibliotheken (Python und TypeScript/JavaScript) sowie die REST API zugänglich. Dazu müssen Sie drei Codezeilen aktualisieren und Ihren Gemini API-Schlüssel verwenden. Wenn Sie noch keine OpenAI-Bibliotheken nutzen, sollten Sie die Gemini API direkt aufrufen.

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-3.8-flash",
    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-3.8-flash",
    messages: [
        {   role: "system",
            content: "You are a helpful assistant." 
        },
        {
            role: "user",
            content: "Explain to me how AI works",
        },
    ],
});

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

REST

curl "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $GEMINI_API_KEY" \
  -d '{
    "model": "gemini-3.8-flash",
    "messages": [
      {
        "role": "user",
        "content": "Explain to me how AI works"
      }
    ]
  }'

Was hat sich geändert? Nur drei Zeilen!

  • api_key="GEMINI_API_KEY": Ersetzen Sie „GEMINI_API_KEY“ durch Ihren tatsächlichen Gemini API-Schlüssel, den Sie in Google AI Studio erhalten.

  • base_url="https://generativelanguage.googleapis.com/v1beta/openai/": Damit wird die OpenAI-Bibliothek angewiesen, Anfragen an den Gemini API-Endpunkt statt an die Standard-URL zu senden.

  • model="gemini-3.8-flash": Wählen Sie ein kompatibles Gemini-Modell aus.

Thinking

Gemini-Modelle sind darauf trainiert, komplexe Probleme zu durchdenken, was zu einer deutlich verbesserten Logik führt. Die Gemini API bietet Thinking-Parameter, mit denen Sie genau steuern können, wie viel das Modell „nachdenkt“.

Verschiedene Gemini-Modelle haben unterschiedliche Reasoning-Konfigurationen. So lassen sie sich den Reasoning-Aufwänden von OpenAI zuordnen:

reasoning_effort (OpenAI) thinking_level (Gemini 4 Argon) thinking_level (Gemini 3.1 Flash-Lite) thinking_level (Gemini 3 Flash) thinking_budget (Gemini 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

Wenn kein reasoning_effort angegeben ist, verwendet Gemini die Standardstufe oder das Standardbudget des Modells.

Wenn Sie das Nachdenken deaktivieren möchten, können Sie reasoning_effort für 2.5-Modelle auf "none" setzen. Die logische Schlussfolgerung kann für Gemini 2.5 Pro- oder Gemini 3-Modelle nicht deaktiviert werden.

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-3.8-flash",
    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-3.8-flash",
    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);

REST

curl "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $GEMINI_API_KEY" \
  -d '{
    "model": "gemini-3.8-flash",
    "reasoning_effort": "low",
    "messages": [
      {
        "role": "user",
        "content": "Explain to me how AI works"
      }
    ]
  }'

Gemini-Modelle mit Denkprozess erstellen auch Zusammenfassungen des Denkprozesses. Mit dem Feld extra_body können Sie Gemini-Felder in Ihre Anfrage aufnehmen.

Beachten Sie, dass sich die Funktionen von reasoning_effort und thinking_level/thinking_budget überschneiden und daher nicht gleichzeitig verwendet werden können.

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-3.8-flash",
    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-3.8-flash",
    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);

REST

curl "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer GEMINI_API_KEY" \
  -d '{
      "model": "gemini-3.8-flash",
        "messages": [{"role": "user", "content": "Explain to me how AI works"}],
        "extra_body": {
          "google": {
            "thinking_config": {
              "thinking_level": "low",
              "include_thoughts": true
            }
          }
        }
      }'

Gemini 3 unterstützt die OpenAI-Kompatibilität für Thought-Signaturen in Chat Completion APIs. Das vollständige Beispiel finden Sie auf der Seite Thought Signatures.

Streaming

Die Gemini API unterstützt Streaming-Antworten.

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-3.8-flash",
  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-3.8-flash",
    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();

REST

curl "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer GEMINI_API_KEY" \
  -d '{
      "model": "gemini-3.8-flash",
      "messages": [
          {"role": "user", "content": "Explain to me how AI works"}
      ],
      "stream": true
    }'

Funktionsaufrufe

Funktionsaufrufe erleichtern es Ihnen, strukturierte Datenausgaben von generativen Modellen zu erhalten. Sie werden in der Gemini API unterstützt.

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-3.8-flash",
  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-3.8-flash",
    messages: messages,
    tools: tools,
    tool_choice: "auto",
  });

  console.log(response);
}

main();

REST

curl "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer GEMINI_API_KEY" \
-d '{
  "model": "gemini-3.8-flash",
  "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"
}'

Bilder verstehen

Gemini-Modelle sind nativ multimodal und bieten erstklassige Leistung bei vielen gängigen Vision-Aufgaben.

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-3.8-flash",
  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-3.8-flash",
      messages: messages,
    });

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

main();

REST

bash -c '
  base64_image=$(base64 -i "Path/to/agi/image.jpeg");
  curl "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions" \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer GEMINI_API_KEY" \
    -d "{
      \"model\": \"gemini-3.8-flash\",
      \"messages\": [
        {
          \"role\": \"user\",
          \"content\": [
            { \"type\": \"text\", \"text\": \"What is in this image?\" },
            {
              \"type\": \"image_url\",
              \"image_url\": { \"url\": \"data:image/jpeg;base64,${base64_image}\" }
            }
          ]
        }
      ]
    }"
'

Image generieren

Generieren Sie ein Bild mit gemini-2.5-flash-image oder gemini-3-pro-image-preview. Unterstützte Parameter sind prompt, model, n, size und response_format. Alle anderen Parameter, die weder hier noch im Abschnitt extra_body aufgeführt sind, werden von der Kompatibilitätsebene ignoriert.

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();

REST

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,
      }'

Video generieren

Verständnis von Audioinhalten

Audioeingabe analysieren:

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-3.8-flash",
    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-3.8-flash",
    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();

REST

bash -c '
  base64_audio=$(base64 -i "/path/to/your/audio/file.wav");
  curl "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions" \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer GEMINI_API_KEY" \
    -d "{
      \"model\": \"gemini-3.8-flash\",
      \"messages\": [
        {
          \"role\": \"user\",
          \"content\": [
            { \"type\": \"text\", \"text\": \"Transcribe this audio file.\" },
            {
              \"type\": \"input_audio\",
              \"input_audio\": {
                \"data\": \"${base64_audio}\",
                \"format\": \"wav\"
              }
            }
          ]
        }
      ]
    }"
'

Strukturierte Ausgabe

Gemini-Modelle können JSON-Objekte in jeder von Ihnen definierten Struktur ausgeben.

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-3.8-flash",
    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-3.8-flash",
  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);

Einbettungen

Texteinbettungen messen die Ähnlichkeit von Textstrings und können mit der Gemini API generiert werden. Sie können gemini-embedding-2-preview für multimodale Einbettungen oder gemini-embedding-001 für reine Texteinbettungen verwenden.

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();

REST

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"
  }'

Batch API

Sie können Batchjobs erstellen, einreichen und ihren Status mit der OpenAI-Bibliothek prüfen.

Sie müssen die JSONL-Datei im OpenAI-Eingabeformat vorbereiten. Beispiel:

{"custom_id": "request-1", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "gemini-3.8-flash", "messages": [{"role": "user", "content": "Tell me a one-sentence joke."}]}}
{"custom_id": "request-2", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "gemini-3.8-flash", "messages": [{"role": "user", "content": "Why is the sky blue?"}]}}

Die OpenAI-Kompatibilität für Batch unterstützt das Erstellen eines Batches, das Monitoring des Jobstatus und das Aufrufen von Batchergebnissen.

Die Kompatibilität für Upload und Download wird derzeit nicht unterstützt. Stattdessen wird im folgenden Beispiel der genai-Client zum Hoch- und Herunterladen von Dateien verwendet, genau wie bei der 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)

Das OpenAI SDK unterstützt auch das Generieren von Einbettungen mit der Batch API. Ersetzen Sie dazu das Feld endpoint der Methode create durch einen Einbettungsendpunkt sowie die Schlüssel url und model in der JSONL-Datei:

# 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"
)

Ein vollständiges Beispiel finden Sie im Abschnitt Batch-Einbettungsgenerierung des OpenAI-Kompatibilitäts-Cookbooks.

Flex- und Priority-Inferenz

Die Gemini API entspricht dem service_tier-Parameter von OpenAI in Name und Logik. Sie erzwingt Limits und leitet den Traffic sowohl für die Flex- als auch für die Priority-Inferenzstufe weiter.

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-3.8-flash",
  messages=[
    {"role": "user", "content": "Write a short poem about clouds."}
  ],
  service_tier="priority" # Or service_tier="flex"
)

print(completion)

Wenn service_tier nicht explizit zugewiesen ist, wird standardmäßig standard verwendet, was für OpenAI default entspricht. Weitere Informationen zu Inferenzstufen finden Sie in der Dokumentation zur Optimierung.

Gemini-Funktionen mit extra_body aktivieren

Es gibt mehrere von Gemini unterstützte Funktionen, die in OpenAI-Modellen nicht verfügbar sind, aber über das Feld extra_body aktiviert werden können.

Parameter Typ Endpunkt Beschreibung
cached_content Text Chat Entspricht dem allgemeinen Inhaltscache von Gemini.
thinking_config Objekt Chat Entspricht der ThinkingConfig von Gemini.
aspect_ratio Text Bilder Seitenverhältnis der Ausgabe (z.B. "16:9", "1:1", "9:16").
generation_config Objekt Bilder Gemini-Generierungskonfigurationsobjekt (z.B. {"responseModalities": ["IMAGE"], "candidateCount": 2}).
safety_settings Liste Bilder Benutzerdefinierte Filter für Sicherheitsschwellenwerte (z.B. [{"category": "HARM_CATEGORY_HATE_SPEECH", "threshold": "BLOCK_NONE"}]).
tools Liste Bilder Aktiviert die Fundierung (z.B. [{"google_search": {}}]). Nur für gemini-3-pro-image-preview.

Beispiel mit extra_body

Hier ein Beispiel für die Verwendung von extra_body zum Festlegen von 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-3.8-flash",
    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())

Modelle auflisten

Rufen Sie eine Liste der verfügbaren Gemini-Modelle ab:

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();

REST

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

Modell abrufen

Gemini-Modell abrufen:

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-3.8-flash")
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-3.8-flash");
  console.log(model.id);
}

main();

REST

curl https://generativelanguage.googleapis.com/v1beta/openai/models/gemini-3.8-flash \
-H "Authorization: Bearer GEMINI_API_KEY"

Aktuelle Beschränkungen

Die Unterstützung für die OpenAI-Bibliotheken befindet sich noch in der Betaphase, während wir die Unterstützung für Funktionen erweitern.

Wenn Sie Fragen zu unterstützten Parametern oder anstehenden Funktionen haben oder Probleme bei den ersten Schritten mit Gemini auftreten, besuchen Sie unser Entwicklerforum.

Nächste Schritte

In unserem Colab zur OpenAI-Kompatibilität finden Sie detailliertere Beispiele.