API Reference

Gemini Generate Content

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

Preview guide

Paste into an AI assistant to help with integration. Documentation and examples only; no real credentials.

# Gemini Generate Content

Gemini Generate Content

## 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 |
| --- | --- | --- | --- |
| contents | array | Yes | Input content, typically organized into parts. Example: [{"parts":[{"text":"你好"}]}] |
| generationConfig.temperature | number | No | Sampling randomness: lower values focus output, higher values increase variety. Usually adjust either temperature or topP. Form initial value (not an upstream default): 0.7 Range in this definition: 0 ~ 2 Example: 0.7 |
| generationConfig.maxOutputTokens | number | No | Maximum output token budget, potentially including Gemini thinking tokens. Low limits can leave little room for visible output; higher limits can increase maximum time and cost. Form initial value (not an upstream default): 512 Range in this definition: 1 ~ 65536 Example: 512 |
| generationConfig.topP | number | No | Cumulative token probability threshold. Usually adjust either topP or temperature. Form initial value (not an upstream default): 0.95 Range in this definition: 0 ~ 1 Example: 0.95 |
| generationConfig.topK | number | No | Sample from the K most probable tokens at each step. Omit to use the model default strategy. Range in this definition: 1 ~ 500 Example: 40 |
| safetySettings | array | No | Optional safety policy settings. Example: [] |
| contents[].role | string | No | user or model. |
| contents[].parts[] | object | No | text, inlineData, fileData or functionCall/functionResponse parts. |
| systemInstruction | object | No | System instruction content. |
| tools | array | No | Tool configuration supported by the model. |

## Minimal request example

```json
{
  "contents": [
    {
      "parts": [
        {
          "text": "Hello"
        }
      ]
    }
  ]
}
```

## 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": "Hello"
        }
      ]
    }
  ]
}'
```

### 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\":\"Hello\"}]}]}")
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": "Hello"
        }
      ]
    }
  ]
}) });
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[] | object | Text, function-call or media parts. |
| usageMetadata | object | Model usage. |

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

```json
{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [
          {
            "text": "Hello"
          }
        ]
      }
    }
  ]
}
```

## Streaming

For SSE use :streamGenerateContent?alt=sse and parse candidates[].content.parts.

## 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.

## Documentation source

Definition version: 1

Reviewed: 2026-11-02

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

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.

Updated 2026-11-02 · Reviewed 2026-11-02

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.

Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

Minimal request example

{
  "contents": [
    {
      "parts": [
        {
          "text": "Hello"
        }
      ]
    }
  ]
}

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.

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.

Path parameters

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

Body parameters

Field	Type	Required	Description / constraints
contents	array	Yes	Input content, typically organized into parts. Example: [{"parts":[{"text":"你好"}]}]
generationConfig.temperature	number	No	Sampling randomness: lower values focus output, higher values increase variety. Usually adjust either temperature or topP. Form initial value (not an upstream default): 0.7 Range in this definition: 0 ~ 2 Example: 0.7
generationConfig.maxOutputTokens	number	No	Maximum output token budget, potentially including Gemini thinking tokens. Low limits can leave little room for visible output; higher limits can increase maximum time and cost. Form initial value (not an upstream default): 512 Range in this definition: 1 ~ 65536 Example: 512
generationConfig.topP	number	No	Cumulative token probability threshold. Usually adjust either topP or temperature. Form initial value (not an upstream default): 0.95 Range in this definition: 0 ~ 1 Example: 0.95
generationConfig.topK	number	No	Sample from the K most probable tokens at each step. Omit to use the model default strategy. Range in this definition: 1 ~ 500 Example: 40
safetySettings	array	No	Optional safety policy settings. Example: []
contents[].role	string	No	user or model.
contents[].parts[]	object	No	text, inlineData, fileData or functionCall/functionResponse parts.
systemInstruction	object	No	System instruction content.
tools	array	No	Tool configuration supported by the model.

Response fields

Field	Type	Description / constraints
candidates[].content.parts[]	object	Text, function-call or media parts.
usageMetadata	object	Model usage.

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

{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [
          {
            "text": "Hello"
          }
        ]
      }
    }
  ]
}

Streaming

For SSE use :streamGenerateContent?alt=sse and parse candidates[].content.parts.

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.

Document information and sources

Documentation source

Definition version: 1

Reviewed: 2026-11-02

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

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.

Request examples

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": "Hello"
        }
      ]
    }
  ]
}'

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\":\"Hello\"}]}]}")
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.

// 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": "Hello"
        }
      ]
    }
  ]
}) });
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.