Gemini Native API

Overview

AIone supports calling the gateway directly using the Google Gemini native API format, suitable for custom gateway aggregation, the Google Gemini SDK, and scenarios where you already have Gemini integration code.

The request and response formats are fully identical to the Google Gemini API. The gateway only handles authentication, routing, and billing — no format conversion is performed.

Connection Details

Item	Value
Base URL	`https://api.nexara.net`
Authentication header	`Authorization: Bearer sk-nex-your-key-here`
Non-streaming endpoint	`POST /v1beta/models/{model}:generateContent`
Streaming endpoint	`POST /v1beta/models/{model}:streamGenerateContent?alt=sse`

Note: Use your AIone API Key (sk-nex-xxx), not a Google API Key.

Supported Models

All connected Gemini models are available through the native API, including:

Text models: gemini-2.5-flash, gemini-2.5-pro, gemini-3-pro-preview, gemini-3-flash-preview, gemini-3.1-pro, etc.

Image generation models: gemini-3.1-flash-image-preview, gemini-3-pro-image-preview, gemini-2.5-flash-image, etc.

For the full list, query GET https://api.nexara.net/v1/models.

Non-Streaming Request — generateContent

Basic Example

Response Format

{
  "candidates": [
    {
      "content": {
        "parts": [{"text": "Quantum computing leverages quantum mechanics principles..."}],
        "role": "model"
      },
      "finishReason": "STOP",
      "index": 0
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 10,
    "candidatesTokenCount": 25,
    "totalTokenCount": 35
  },
  "modelVersion": "gemini-2.5-flash"
}

Image Generation Example

Images are returned as inlineData (base64-encoded) in the candidates[0].content.parts[] of the response.

Note: 4K image generation may take 2-3 minutes. Set your client's HTTP timeout to at least 600 seconds.

Streaming Request — streamGenerateContent

Append ?alt=sse to the endpoint URL. The response is returned as SSE (Server-Sent Events) chunks.

Example

SSE Response Format

data: {"candidates":[{"content":{"parts":[{"text":"Spring"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":8,"candidatesTokenCount":2,"totalTokenCount":10}}

data: {"candidates":[{"content":{"parts":[{"text":" breeze blows,"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":8,"candidatesTokenCount":5,"totalTokenCount":13}}

data: {"candidates":[{"content":{"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":8,"candidatesTokenCount":28,"totalTokenCount":36}}

Each data: line is an independent JSON object. usageMetadata values are cumulative — the last chunk contains the final usage totals.

Note: Image generation models do not support streamGenerateContent. Use generateContent instead.

Python SDK Example

Node.js SDK Example

Note: The official Google SDK may not directly support custom endpoints. If you encounter this limitation, we recommend using direct HTTP calls or a third-party library that supports custom Base URLs.

Comparison with OpenAI-Compatible Format

Dimension	Gemini Native Format	OpenAI-Compatible Format
Endpoint	`/v1beta/models/{model}:generateContent`	`/v1/chat/completions`
Request body	`contents` + `generationConfig`	`messages` + `max_tokens`
Response body	`candidates` + `usageMetadata`	`choices` + `usage`
Image parameters	`imageConfig.imageSize` / `imageConfig.aspectRatio`	`image_size` / `aspect_ratio`
Streaming	`:streamGenerateContent?alt=sse`	`"stream": true`
Best for	Custom gateway aggregation, existing Gemini code	General-purpose clients, IDE plugins

Both formats access the same set of models and upstream channels. Choose based on your client's requirements.

Limitations & Notes

Authentication: Use your AIone sk-nex- API Key, not a Google API Key

Image models do not support streaming: streamGenerateContent returns 503 for image generation models — use generateContent instead

Supported actions: Only generateContent and streamGenerateContent are supported; countTokens, embedContent, etc. are not available

Timeout settings: For image generation (especially 4K), set your HTTP timeout to at least 600 seconds

Byte-level passthrough: Both requests and responses are passed through at the byte level — the gateway performs no format conversion

15 - Gemini Native API

Gemini Native API#

Overview#

Connection Details#

Supported Models#

Non-Streaming Request — generateContent#

Basic Example#

Response Format#

Image Generation Example#

Streaming Request — streamGenerateContent#

Example#

SSE Response Format#

Python SDK Example#

Node.js SDK Example#

Comparison with OpenAI-Compatible Format#

Limitations & Notes#