Gemini

Get Your API Key

Go to the API Keys page to create your API key.

API Base URL

https://tokenoff.com/api

Gemini models are accessed via the Gemini API, fully compatible with the Google Generative AI API.

curl

Blocking

curl https://tokenoff.com/api/v1beta/models/gemini-2.5-pro:generateContent \
  -H "Authorization: Bearer your_api_key_here" \
  -H "Content-Type: application/json" \
  -d '{
      "contents": [
          {
              "role": "user",
              "parts": [
                  {"text": "Hello"}
              ]
          }
      ]
  }'

Output:

{
  "candidates": [
    {
      "content": {
        "parts": [
          {
            "text": "Hello! How can I help you today?"
          }
        ],
        "role": "model"
      },
      "finishReason": "STOP",
      "index": 0
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 2,
    "candidatesTokenCount": 9,
    "totalTokenCount": 342,
    "promptTokensDetails": [
      {
        "modality": "TEXT",
        "tokenCount": 2
      }
    ],
    "thoughtsTokenCount": 331
  },
  "modelVersion": "gemini-2.5-pro",
  "responseId": "3-3gafT1A7mn1MkP1qHryAc"
}

Streaming

curl https://tokenoff.com/api/v1beta/models/gemini-2.5-pro:streamGenerateContent \
  -H "Authorization: Bearer your_api_key_here" \
  -H "Content-Type: application/json" \
  -d '{
      "contents": [
          {
              "role": "user",
              "parts": [
                  {"text": "Hello"}
              ]
          }
      ]
  }'

Output:

data: {"candidates": [{"content": {"parts": [{"text": "Hello there! How can I help you today?"}],"role": "model"},"index": 0}],"usageMetadata": {"promptTokenCount": 2,"candidatesTokenCount": 10,"totalTokenCount": 424,"promptTokensDetails": [{"modality": "TEXT","tokenCount": 2}],"thoughtsTokenCount": 412},"modelVersion": "gemini-2.5-pro","responseId": "I-7gaaaYE92p1MkPkPr1wAM"}

data: {"candidates": [{"content": {"role": "model"},"finishReason": "STOP","index": 0}],"usageMetadata": {"promptTokenCount": 2,"candidatesTokenCount": 10,"totalTokenCount": 424,"promptTokensDetails": [{"modality": "TEXT","tokenCount": 2}],"thoughtsTokenCount": 412},"modelVersion": "gemini-2.5-pro","responseId": "I-7gaaaYE92p1MkPkPr1wAM"}

Python

pip install google-genai

Blocking

from google import genai

client = genai.Client(
  api_key="your_api_key_here",
  http_options=genai.types.HttpOptions(
      base_url="https://tokenoff.com/api",
  ),
)

response = client.models.generate_content(
  model="gemini-2.5-pro",
  contents="Hello",
)

print(response.text)

Output:

Hello there! How can I help you today?

Streaming

from google import genai

client = genai.Client(
  api_key="your_api_key_here",
  http_options=genai.types.HttpOptions(
      base_url="https://tokenoff.com/api",
  ),
)

response = client.models.generate_content_stream(
  model="gemini-2.5-pro",
  contents="Hello",
)

for chunk in response:
  print(chunk)

Output:

sdk_http_response=HttpResponse(
  headers=<dict len=11>
) candidates=[Candidate(
  content=Content(
    parts=[
      Part(
        text='Hello there! How can I help you today?'
      ),
    ],
    role='model'
  ),
  index=0
)] create_time=None model_version='gemini-2.5-pro' prompt_feedback=None response_id='KvDgaZalJPqk1MkP4u3XkQc' usage_metadata=GenerateContentResponseUsageMetadata(
  candidates_token_count=10,
  prompt_token_count=2,
  prompt_tokens_details=[
    ModalityTokenCount(
      modality=<MediaModality.TEXT: 'TEXT'>,
      token_count=2
    ),
  ],
  thoughts_token_count=511,
  total_token_count=523
) model_status=None automatic_function_calling_history=None parsed=None

sdk_http_response=HttpResponse(
  headers=<dict len=11>
) candidates=[Candidate(
  content=Content(
    role='model'
  ),
  finish_reason=<FinishReason.STOP: 'STOP'>,
  index=0
)] create_time=None model_version='gemini-2.5-pro' prompt_feedback=None response_id='KvDgaZalJPqk1MkP4u3XkQc' usage_metadata=GenerateContentResponseUsageMetadata(
  candidates_token_count=10,
  prompt_token_count=2,
  prompt_tokens_details=[
    ModalityTokenCount(
      modality=<MediaModality.TEXT: 'TEXT'>,
      token_count=2
    ),
  ],
  thoughts_token_count=511,
  total_token_count=523
) model_status=None automatic_function_calling_history=None parsed=None

TypeScript

npm install @google/genai

Blocking

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({
  apiKey: "your_api_key_here",
  httpOptions: {
      baseUrl: "https://tokenoff.com/api",
  },
});

const response = await ai.models.generateContent({
  model: "gemini-2.5-pro",
  contents: "Hello",
});

console.log(response.text);

Output:

Hello! How can I help you today?

Streaming

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({
  apiKey: "your_api_key_here",
  httpOptions: {
      baseUrl: "https://tokenoff.com/api",
  },
});

const response = await ai.models.generateContentStream({
  model: "gemini-2.5-pro",
  contents: "Hello",
});

for await (const event of response) {
console.log(event);
}

Output:

GenerateContentResponse {
  candidates: [ { content: [Object], index: 0 } ],
  modelVersion: 'gemini-2.5-pro',
  responseId: '6vHgaYq7H9qk1MkPxqDcqQ0',
  usageMetadata: {
    promptTokenCount: 2,
    candidatesTokenCount: 4,
    totalTokenCount: 344,
    promptTokensDetails: [ [Object] ],
    thoughtsTokenCount: 338
  },
  sdkHttpResponse: {
    headers: {
      'alt-svc': 'h3=":443"; ma=2592000, h3-29=":443"; ma=2592000',
      'content-disposition': 'attachment',
      'content-type': 'text/event-stream',
      date: 'Thu, 16 Apr 2026 14:27:57 GMT',
      server: 'scaffolding, on, HTTPServer2',
      'server-timing': 'gfet4t7; dur=4180',
      'transfer-encoding': 'chunked',
      vary: 'Origin, X-Origin, Referer',
      'x-content-type-options': 'nosniff',
      'x-frame-options': 'SAMEORIGIN',
      'x-xss-protection': '0'
    }
  }
}

GenerateContentResponse {
  candidates: [ { content: [Object], finishReason: 'STOP', index: 0 } ],
  modelVersion: 'gemini-2.5-pro',
  responseId: '6vHgaYq7H9qk1MkPxqDcqQ0',
  usageMetadata: {
    promptTokenCount: 2,
    candidatesTokenCount: 9,
    totalTokenCount: 349,
    promptTokensDetails: [ [Object] ],
    thoughtsTokenCount: 338
  },
  sdkHttpResponse: {
    headers: {
      'alt-svc': 'h3=":443"; ma=2592000, h3-29=":443"; ma=2592000',
      'content-disposition': 'attachment',
      'content-type': 'text/event-stream',
      date: 'Thu, 16 Apr 2026 14:27:57 GMT',
      server: 'scaffolding, on, HTTPServer2',
      'server-timing': 'gfet4t7; dur=4180',
      'transfer-encoding': 'chunked',
      vary: 'Origin, X-Origin, Referer',
      'x-content-type-options': 'nosniff',
      'x-frame-options': 'SAMEORIGIN',
      'x-xss-protection': '0'
    }
  }
}

Supported Models

Contact Us

If you encounter any issues while using TokenOff:

Contact us atsupport@tokenoff.comand other official channels for technical support
Submit an issue on ourGithubrepository

Gemini

gemini-3.1-pro-preview

gemini-3-flash-preview

gemini-2.5-pro

gemini-2.5-flash

gemini-2.5-flash-lite

On this page