# Gemini Image Generation

Generate images through Gemini generateContent; responses may contain both text and image parts.

## Endpoint and authentication

`POST https://api.tu-zi.com/v1beta/models/{model}:generateContent`

Transport: json

Use an inference API key. Examples contain placeholders; read credentials from environment variables.

```http
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json
```

## Path parameters

| Field | Type | Required | Description / constraints |
| --- | --- | --- | --- |
| model | string | Yes | Selected model identifier. Example: YOUR_MODEL |

## Body parameters

| Field | Type | Required | Description / constraints |
| --- | --- | --- | --- |
| prompt | string | Yes | Image generation or editing prompt. |
| response_modalities | array[string] | Yes | Request image content in the response. |
| aspect_ratio | string | No | Generated image aspect ratio. Values: "1:1", "16:9", "9:16", "4:3", "3:4" |
| image_size | string | No | Output resolution supported by Gemini 3 image models. Values: "1K", "2K", "4K" |

## Minimal request example

```json
{
  "contents": [
    {
      "parts": [
        {
          "text": "Draw a cat"
        }
      ]
    }
  ],
  "generationConfig": {
    "responseModalities": [
      "TEXT",
      "IMAGE"
    ]
  }
}
```

## Before running

Replace https://api.tu-zi.com with this site origin (do not append /v1 twice), and YOUR_MODEL with the exact marketplace model ID. Install requests for Python; use Node.js 20+ and save JavaScript as .mjs. WebSocket samples list their own dependencies.

Create an inference key on the site and set API_KEY in the environment; replace YOUR_API_KEY in cURL. Prepare local input.png/input.wav files for upload examples.

Start with a minimal request, then read the result using the response fields below. For async APIs, a returned task ID requires polling; acceptance does not mean generation has finished.

## Code examples

### curl

```bash
curl --request POST 'https://api.tu-zi.com/v1beta/models/YOUR_MODEL:generateContent' \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
  "contents": [
    {
      "parts": [
        {
          "text": "Draw a cat"
        }
      ]
    }
  ],
  "generationConfig": {
    "responseModalities": [
      "TEXT",
      "IMAGE"
    ]
  }
}'
```

### python

```python
import json
import os
import requests

url = "https://api.tu-zi.com/v1beta/models/YOUR_MODEL:generateContent"
headers = json.loads("{\"Authorization\":\"Bearer YOUR_API_KEY\",\"Content-Type\":\"application/json\"}")
headers["Authorization"] = "Bearer " + os.environ["API_KEY"]
payload = json.loads("{\"contents\":[{\"parts\":[{\"text\":\"Draw a cat\"}]}],\"generationConfig\":{\"responseModalities\":[\"TEXT\",\"IMAGE\"]}}")
response = requests.request("POST", url, headers=headers, json=payload, timeout=120)
response.raise_for_status()
result = response.json()
if isinstance(result, dict) and (result.get("success") is False or result.get("error")):
    raise RuntimeError(json.dumps(result, ensure_ascii=False))
print(result)  # Also inspect protocol-specific status/code fields.
```

### javascript

```javascript
// Node.js 20+
const url = "https://api.tu-zi.com/v1beta/models/YOUR_MODEL:generateContent";
const headers = {
  "Authorization": "Bearer YOUR_API_KEY",
  "Content-Type": "application/json"
};
headers.Authorization = 'Bearer ' + process.env.API_KEY;
const response = await fetch(url, { method: "POST", headers, body: JSON.stringify({
  "contents": [
    {
      "parts": [
        {
          "text": "Draw a cat"
        }
      ]
    }
  ],
  "generationConfig": {
    "responseModalities": [
      "TEXT",
      "IMAGE"
    ]
  }
}) });
if (!response.ok) throw new Error(await response.text());
const result = await response.json();
if (result?.success === false || result?.error) throw new Error(JSON.stringify(result));
console.log(result); // Also inspect protocol-specific status/code fields.
```

## Response fields

| Field | Type | Description / constraints |
| --- | --- | --- |
| candidates[].content.parts[].text | string | Optional text part; text alone does not prove an image was generated. |
| candidates[].content.parts[].inlineData.mimeType | string | Inline image MIME, such as image/png, image/jpeg or image/webp. |
| candidates[].content.parts[].inlineData.data | string | Base64-encoded image bytes to decode and save, not a URL. |
| candidates[].content.parts[].fileData.fileUri | string | Optional file reference. Only accessible HTTP(S) URLs can be downloaded directly; gs:// and similar references require the corresponding storage access. |
| candidates[].finishReason / promptFeedback.blockReason | string | Completion or blocking reason; inspect when no valid image is present instead of blindly resubmitting. |
| usageMetadata | object | Model usage, not proof that an image was generated. |

Illustrative response; some endpoints show essential fields only. Optional fields may be absent.

```json
{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [
          {
            "text": "Here is the image."
          },
          {
            "inlineData": {
              "mimeType": "image/png",
              "data": "BASE64_IMAGE_BYTES"
            }
          }
        ]
      },
      "finishReason": "STOP"
    }
  ]
}
```

## Errors and retries

Check HTTP status and protocol-specific errors; do not mix error formats across protocols. For 401/403 check credentials and permissions, for 429 back off, and for 5xx check gateway/upstream status. Error bodies may contain error/message/code depending on the protocol.

Use bounded exponential backoff for reads. Do not blindly retry task creation, generation, or key mutations, to avoid duplicate billing or execution.

## Constraints

This page describes the base protocol. Use the selected model quick start for supported fields, enums, limits and asynchronous behavior. Replace YOUR_MODEL. Form initial values are not upstream defaults. The model ID belongs in the URL path. Use contents[].parts[] and generationConfig.responseModalities, not OpenAI messages or data[].url response assumptions. Iterate all candidates[].content.parts[], read inlineData.mimeType and inlineData.data, and validate image/*, Base64 and decoded image bytes before saving. Compatible upstreams may return inline_data/mime_type. HTTP(S) fileData.fileUri can be downloaded; non-HTTP(S) references need separate access. Do not send the site API key to download URLs. Text-only output, empty candidates or no valid image must not be reported as image success; inspect finishReason, promptFeedback and errors. BASE64_IMAGE_BYTES is only an illustrative placeholder.

## Documentation source

Definition version: 1

Reviewed: 2026-11-02

Source: https://api.tu-zi.com/en/docs/api/reference-relay-gemini-image

Related protocol guide: https://api.tu-zi.com/docs/api/gemini

This export contains documentation and examples only, without real credentials, account data or user requests.