> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://respan.ai/docs/apis/gateway/generate-google-model-content/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://respan.ai/_mcp/server.

# Generate Google model content

POST https://api.respan.ai/api/google/{sdk_type}/v1beta/models/{model_name}:{render_format}
Content-Type: application/json

Send native Google Gen AI or Vertex AI requests through Respan using provider credentials configured in Respan. Authenticate with your Respan key in `x-goog-api-key`.

Reference: https://respan.ai/docs/apis/gateway/generate-google-model-content

## Request

### Path parameters

- `sdk_type` (enum, required)
  - Allowed values: `gemini`, `vertexai`
- `model_name` (string, required)
- `render_format` (enum, required)
  - Allowed values: `generateContent`, `streamGenerateContent`

### Headers

- `x-goog-api-key` (string, required) — Your Respan API key in Google's native authentication header.

### Body (application/json)

This endpoint expects a map from string to any.

- `map from string to any`

## Response

### 200

Google response or event stream.

- `map from string to any`

## Errors

### 400 Bad Request Error

Invalid request.

- `map from string to any`

### 402 Payment Required Error

Insufficient credits.

- `map from string to any`

### 403 Forbidden Error

The API key is missing, invalid or expired.

- `detail` (string, required)

### 424 Failed Dependency Error

Upstream provider failed.

- `map from string to any`

### 429 Too Many Requests Error

Rate limit exceeded.

- `map from string to any`

## Examples

**Request**

```json
{
  "contents": [
    {
      "role": "user",
      "parts": [
        {
          "text": "Explain how AI works in a few words."
        }
      ]
    }
  ]
}
```

**Response**

```json
{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [
          {
            "text": "AI learns patterns from data to make predictions and generate responses."
          }
        ]
      },
      "finishReason": "STOP",
      "index": 0
    }
  ]
}
```

**SDK Code**

```python Google Gateway_api_google_v1beta_models_:_create_example
import requests

url = "https://api.respan.ai/api/google/gemini/v1beta/models/gemini-3.5-flash:generateContent"

payload = { "contents": [
        {
            "role": "user",
            "parts": [{ "text": "Explain how AI works in a few words." }]
        }
    ] }
headers = {
    "x-goog-api-key": "YOUR_RESPAN_API_KEY",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.json())
```

```javascript Google Gateway_api_google_v1beta_models_:_create_example
const url = 'https://api.respan.ai/api/google/gemini/v1beta/models/gemini-3.5-flash:generateContent';
const options = {
  method: 'POST',
  headers: {'x-goog-api-key': 'YOUR_RESPAN_API_KEY', 'Content-Type': 'application/json'},
  body: '{"contents":[{"role":"user","parts":[{"text":"Explain how AI works in a few words."}]}]}'
};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}
```

```go Google Gateway_api_google_v1beta_models_:_create_example
package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.respan.ai/api/google/gemini/v1beta/models/gemini-3.5-flash:generateContent"

	payload := strings.NewReader("{\n  \"contents\": [\n    {\n      \"role\": \"user\",\n      \"parts\": [\n        {\n          \"text\": \"Explain how AI works in a few words.\"\n        }\n      ]\n    }\n  ]\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("x-goog-api-key", "YOUR_RESPAN_API_KEY")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(res)
	fmt.Println(string(body))

}
```

```ruby Google Gateway_api_google_v1beta_models_:_create_example
require 'uri'
require 'net/http'

url = URI("https://api.respan.ai/api/google/gemini/v1beta/models/gemini-3.5-flash:generateContent")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["x-goog-api-key"] = 'YOUR_RESPAN_API_KEY'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"contents\": [\n    {\n      \"role\": \"user\",\n      \"parts\": [\n        {\n          \"text\": \"Explain how AI works in a few words.\"\n        }\n      ]\n    }\n  ]\n}"

response = http.request(request)
puts response.read_body
```

```java Google Gateway_api_google_v1beta_models_:_create_example
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.post("https://api.respan.ai/api/google/gemini/v1beta/models/gemini-3.5-flash:generateContent")
  .header("x-goog-api-key", "YOUR_RESPAN_API_KEY")
  .header("Content-Type", "application/json")
  .body("{\n  \"contents\": [\n    {\n      \"role\": \"user\",\n      \"parts\": [\n        {\n          \"text\": \"Explain how AI works in a few words.\"\n        }\n      ]\n    }\n  ]\n}")
  .asString();
```

```php Google Gateway_api_google_v1beta_models_:_create_example
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('POST', 'https://api.respan.ai/api/google/gemini/v1beta/models/gemini-3.5-flash:generateContent', [
  'body' => '{
  "contents": [
    {
      "role": "user",
      "parts": [
        {
          "text": "Explain how AI works in a few words."
        }
      ]
    }
  ]
}',
  'headers' => [
    'Content-Type' => 'application/json',
    'x-goog-api-key' => 'YOUR_RESPAN_API_KEY',
  ],
]);

echo $response->getBody();
```

```csharp Google Gateway_api_google_v1beta_models_:_create_example
using RestSharp;

var client = new RestClient("https://api.respan.ai/api/google/gemini/v1beta/models/gemini-3.5-flash:generateContent");
var request = new RestRequest(Method.POST);
request.AddHeader("x-goog-api-key", "YOUR_RESPAN_API_KEY");
request.AddHeader("Content-Type", "application/json");
request.AddParameter("application/json", "{\n  \"contents\": [\n    {\n      \"role\": \"user\",\n      \"parts\": [\n        {\n          \"text\": \"Explain how AI works in a few words.\"\n        }\n      ]\n    }\n  ]\n}", ParameterType.RequestBody);
IRestResponse response = client.Execute(request);
```

```swift Google Gateway_api_google_v1beta_models_:_create_example
import Foundation

let headers = [
  "x-goog-api-key": "YOUR_RESPAN_API_KEY",
  "Content-Type": "application/json"
]
let parameters = ["contents": [
    [
      "role": "user",
      "parts": [["text": "Explain how AI works in a few words."]]
    ]
  ]] as [String : Any]

let postData = JSONSerialization.data(withJSONObject: parameters, options: [])

let request = NSMutableURLRequest(url: NSURL(string: "https://api.respan.ai/api/google/gemini/v1beta/models/gemini-3.5-flash:generateContent")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 10.0)
request.httpMethod = "POST"
request.allHTTPHeaderFields = headers
request.httpBody = postData as Data

let session = URLSession.shared
let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in
  if (error != nil) {
    print(error as Any)
  } else {
    let httpResponse = response as? HTTPURLResponse
    print(httpResponse)
  }
})

dataTask.resume()
```