Gemini Native API

Gemini Native API supports text generation, multi-turn conversations, image understanding, PDF analysis, and multimodal capabilities.

Generate Content

Non-streaming content generation that returns the complete response at once.

Generate Content

post

Non-streaming content generation. Returns complete response at once. Supports text conversations, image understanding, PDF analysis, and multimodal inputs.

Authorizations

BearerAuth

AuthorizationstringRequired

Authenticate using Bearer Token. Get API Key at https://viralapi.ai/api-key

Path parameters

modelstring · enumRequired

Model name

Example: gemini-3-flash-previewPossible values:

Body

application/json

Responses

200

Generation successful

application/json

400

Invalid request parameters

application/json

401

Authentication failed

application/json

403

Insufficient permissions

application/json

500

Internal server error

application/json

post

/v1beta/models/{model}:generateContent

HTTPcURLJavaScriptPython

POST /v1beta/models/{model}:generateContent HTTP/1.1
Host: viralapi.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 147

{
  "contents": [
    {
      "role": "user",
      "parts": [
        {
          "text": "Hello, please introduce yourself"
        }
      ]
    }
  ],
  "generationConfig": {
    "maxOutputTokens": 16384,
    "temperature": 0.7
  }
}

{
  "candidates": [
    {
      "content": {
        "parts": [
          {
            "text": "Hello! I'm Gemini, a multimodal AI assistant developed by Google. I can help you with various tasks, including answering questions, analyzing images, understanding documents, and more. How can I assist you today?"
          }
        ],
        "role": "model"
      },
      "finishReason": "STOP",
      "index": 0
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 10,
    "candidatesTokenCount": 85,
    "totalTokenCount": 95
  }
}

Stream Generate Content

Streaming content generation using SSE (Server-Sent Events). Returns partial responses progressively.

Note: Remember to add ?alt=sse query parameter to enable streaming output.

Stream Generate Content

post

Streaming content generation. Returns responses progressively via SSE (Server-Sent Events). Suitable for long text generation scenarios where users can see the generation process in real-time. Requires ?alt=sse query parameter.

Authorizations

BearerAuth

AuthorizationstringRequired

Authenticate using Bearer Token. Get API Key at https://viralapi.ai/api-key

Path parameters

modelstring · enumRequired

Model name

Example: gemini-3-flash-previewPossible values:

Query parameters

altstring · enumRequired

Output format, must be set to sse to enable streaming output

Example: ssePossible values:

Body

application/json

Responses

200

Streaming generation successful, returns SSE event stream

text/event-stream

Responsestring

SSE format event stream, each event contains partial generated content

400

Invalid request parameters

application/json

401

Authentication failed

application/json

403

Insufficient permissions

application/json

500

Internal server error

application/json

post

/v1beta/models/{model}:streamGenerateContent

HTTPcURLJavaScriptPython

POST /v1beta/models/{model}:streamGenerateContent?alt=sse HTTP/1.1
Host: viralapi.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 140

{
  "contents": [
    {
      "role": "user",
      "parts": [
        {
          "text": "Write an article about AI"
        }
      ]
    }
  ],
  "generationConfig": {
    "maxOutputTokens": 16384,
    "temperature": 0.7
  }
}

data: {"candidates":[{"content":{"parts":[{"text":"Artificial Intelligence"}],"role":"model"},"index":0}]}

data: {"candidates":[{"content":{"parts":[{"text":" (AI) is"}],"role":"model"},"index":0}]}

data: {"candidates":[{"content":{"parts":[{"text":" transforming the world..."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12,"candidatesTokenCount":500,"totalTokenCount":512}}