### Run Setup Wizard

Source: https://docs.venice.ai/guides/integrations/nanoclaw-venice

Execute this command in your Claude Code terminal to start the NanoClaw setup wizard. The wizard guides you through bootstrapping, API key validation, channel selection, container building, and service setup.

```text
/setup
```

--------------------------------

### Reference Workflow Examples

Source: https://docs.venice.ai/guides/media/seedance-2-0

Provides concrete examples of using the reference workflow. These demonstrate how to specify subject, scene, or audio characteristics from uploaded media to guide video generation.

```text
Refer to <Subject 1> in <Image 1> to generate a 5-second clip of the same character riding a horse through snow.
```

```text
Refer to the camera scene in <Video 1> to generate a similar establishing shot of a futuristic city at dawn.
```

```text
Refer to <Subject 1> in <Image 1> and use the timbre in <Audio 1> for the narrator describing the scene. (audio donors must be paired with at least one image or video reference — audio alone is rejected)
```

--------------------------------

### Setting up CrewAI

Source: https://docs.venice.ai/guides/integrations/crewai

Install CrewAI and necessary dependencies to get started with building autonomous agents.

```python
pip install 'crewai[tools]'
```

--------------------------------

### Install Dependencies

Source: https://docs.venice.ai/guides/projects/private-rag-bot

Install the OpenAI Python SDK and Qdrant's Python client with FastEmbed support. This setup is required for the RAG bot.

```shellscript
pip install openai qdrant-client fastembed
```

--------------------------------

### Start Application Initialization

Source: https://docs.venice.ai/api-reference/endpoint/audio/complete

The main function to start the application. It calls initial setup functions and then sets up an observer for DOM changes. It also includes retry logic for specific page elements that might load late.

```javascript
function start() {
  tryInitAll();
  setupObserver();
  
  // Retry for pages where elements may load late
  retryInit('pricing', () => pageInitializers.pricing.initialized, tryInitPricing);
  retryInit('deprecation', () => pageInitializers.deprecations.initialized, tryInitDeprecations);
  retryInit('deprecation', () => pageInitializers.traitsList.initialized, tryInitTraitsList);
  retryInit('beta-models', () => pageInitializers.betaModels.initialized, tryInitBetaModels);
  retryInit('prompt-caching', () => pageInitializers.cachePricing.initialized, tryInitCachePricing);
  retryInit('reasoning-models', () => pageInitializers.reasoningModels.initialized, tryInitReasoningModels);
  retryInit('text-to-speech', () => pageInitializers.voicePicker.initialized, tryInitVoicePicker);
 }
```

--------------------------------

### Node.js Example: Setting Up API Request Options

Source: https://docs.venice.ai/overview/getting-started

This Node.js example shows how to define the URL, method, and headers for an API request to Venice AI. It's a common setup for making POST requests.

```javascript
const url = 'https://api.venice.ai/api/v1/embeddings';
const options = {
 method: 'POST',
 headers: {
 'Authorization': 
```

--------------------------------

### Example API Parameters

Source: https://docs.venice.ai/overview/getting-started

This snippet shows an example of parameters that can be passed to the API for controlling text generation. It includes settings for temperature, max tokens, top_p, frequency penalty, and presence penalty, along with custom parameters for Venice.

```json
{
  "temperature": 0.8,
  "max_tokens": 500,
  "top_p": 0.9,
  "frequency_penalty": 0.5,
  "presence_penalty": 0.5,
  "extra_body": {
    "venice_parameters": {
      "include_venice_system_prompt": False
    }
  }
}
```

--------------------------------

### Initialize OpenAI Client in Node.js

Source: https://docs.venice.ai/overview/getting-started

This Node.js snippet shows how to import and initialize the OpenAI client. Ensure you have the 'openai' package installed.

```javascript
import OpenAI from 'openai';

const client = new OpenAI({
  // This is the default and can be omitted
  apiKey: process.env.OPENAI_API_KEY,
});
```

--------------------------------

### Python Example: Basic API Call

Source: https://docs.venice.ai/overview/getting-started

This snippet demonstrates a basic API call to Venice AI using Python. It shows how to construct the request payload with model and response format. Ensure you have the necessary libraries installed.

```python
import json

response = client.chat.completions.create(
    model="nvidia/parakeet-tdt-0.6b-v3",
    response_format={ "type": "json" },
)
print(response.json())
```

--------------------------------

### Initialize Venice AI Client

Source: https://docs.venice.ai/overview/getting-started

This snippet shows how to import and initialize the Venice AI client. Ensure you have the 'openai' package installed.

```javascript
import OpenAI from 'openai';

```

--------------------------------

### Text-to-Speech Request Example

Source: https://docs.venice.ai/overview/getting-started

This example demonstrates how to construct a JSON payload for the text-to-speech API. It specifies the input text, the desired model ('tts-kokoro'), and the voice ('af_sky').

```json
_jsx(_components.span, {\n style: {\n color: \"#0A3069\",\n \"--shiki-dark\": \"#CE9178\"\n },\n children: \" '{\"\n })\n }), \"\\n\", 
_jsx(_components.span, {\n className: \"line\",\n children: _jsx(_components.span, {\n style: {\n color: \"#0A3069\",\n \"--shiki-dark\": \"#CE9178\"\n },\n children: \" \\\
```

--------------------------------

### Install OpenAI Python SDK

Source: https://docs.venice.ai/overview/getting-started

Install the OpenAI Python SDK using pip. This SDK is compatible with the Venice API and can be used for making requests.

```python
pip install openai
```

--------------------------------

### Python API Client Setup

Source: https://docs.venice.ai/overview/getting-started

Initialize the OpenAI client with your Venice API key and base URL. Ensure your VENICE_API_KEY environment variable is set.

```python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("VENICE_API_KEY"),
    base_url="https://api.venice.ai/api/v1"
)

```

--------------------------------

### Install OpenAI SDK with npm

Source: https://docs.venice.ai/overview/getting-started

Install the OpenAI Node.js SDK to interact with Venice AI. This SDK is compatible with Venice AI due to its OpenAI compatibility.

```shellscript
npm install openai
```

--------------------------------

### Create a Chat Completion Stream

Source: https://docs.venice.ai/overview/getting-started

Use the client to create a chat completion stream. This example uses the 'zai-org-glm-5' model and sends a user message.

```javascript
const stream = await client.chat.completions.create({
  model: 'zai-org-glm-5',
  messages: [{ 
    role: 'user',
    content: 'Write a short story about AI'
  }],
  stream: true
});
```

--------------------------------

### Create a Chat Completion

Source: https://docs.venice.ai/overview/getting-started

Make a request to the chat completions endpoint to generate text. This example uses the 'zai-org-glm-5' model.

```javascript
const completion = await client.chat.completions.create({
  model: 'zai-org-glm-5',
});
```

--------------------------------

### Analyze Image with Text

Source: https://docs.venice.ai/overview/getting-started

This example demonstrates how to use a vision-capable model to analyze an image by providing both text and an image URL. Ensure your API key is set.

```Python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("VENICE_API_KEY"),
    base_url="https://api.venice.ai/api/v1"
)

response = client.chat.completions.create(
    model="qwen3-vl-235b-a22b",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What is in this image?"},
                {
                    "type": "image_url",
                    "image_url": {"url": "https://www.gstatic.com/webp/gallery/1.jpg"}
                }
            ]
        }
    ]
)

print(response.choices[0].message.content)

```

--------------------------------

### Create Chat Completion Request

Source: https://docs.venice.ai/overview/getting-started

Example of how to structure a request to the chat completions API, specifying the model and messages.

```javascript
client.chat.completions.create(
  {
    model: "qwen3-vl-235b-a22b",
    messages: [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "What is in this image?"
          },
          {
            "type": "image_url"
          }
        ]
      }
    ]
  }
)
```

--------------------------------

### Make a Chat Completion Call

Source: https://docs.venice.ai/overview/getting-started

Use the initialized client to make a chat completion request. This example demonstrates a basic call to the chat completions endpoint.

```javascript
const completion = await client.chat.completions.completions({
  model: 'gpt-3.5-turbo',
  messages: [
    { role: 'user', content: 'Hello world' },
  ],
});
```

--------------------------------

### Create Chat Completion with Qwen Model

Source: https://docs.venice.ai/overview/getting-started

Example of creating a chat completion using the Qwen model. This snippet demonstrates how to specify the model, messages, and content for the request.

```javascript
client.chat.completions.create(
  {
    model: "qwen3-vl-235b-a22b",
    messages: [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "What is in this image?"
          }
        ]
      }
    ]
  }
)
```

--------------------------------

### Basic cURL Request Example

Source: https://docs.venice.ai/overview/getting-started

A simple cURL command to demonstrate making a request. This is useful for testing API endpoints from the command line.

```shellscript
curl 
```

--------------------------------

### Basic Chat Completion

Source: https://docs.venice.ai/overview/getting-started

This is a fundamental example of how to send a prompt to the API and receive a completion. Ensure your VENICE_API_KEY environment variable is set.

```Python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("VENICE_API_KEY"),
    base_url="https://api.venice.ai/api/v1"
)

completion = client.chat.completions.create(
    model="zai-org-glm-5",
    messages=[
        {"role": "system", "content": "You are a helpful AI assistant"},
        {"role": "user", "content": "Why is privacy important?"}
    ]
)

print(completion.choices[0].message.content)

```

--------------------------------

### Main Start Function and Initialization

Source: https://docs.venice.ai/api-reference/endpoint/augment/scrape

Orchestrates the initial setup by calling tryInitAll and setupObserver. It also sets up retry logic for specific page elements that might load late.

```javascript
function start() {
  tryInitAll();
  setupObserver();
  
  // Retry for pages where elements may load late
  retryInit('pricing', () => pageInitializers.pricing.initialized, tryInitPricing);
  retryInit('deprecation', () => pageInitializers.deprecations.initialized, tryInitDeprecations);
  retryInit('deprecation', () => pageInitializers.traitsList.initialized, tryInitTraitsList);
  retryInit('beta-models', () => pageInitializers.betaModels.initialized, tryInitBetaModels);
  retryInit('prompt-caching', () => pageInitializers.cachePricing.initialized, tryInitCachePricing);
  retryInit('reasoning-models', () => pageInitializers.reasoningModels.initialized, tryInitReasoningModels);
  retryInit('text-to-speech', () => pageInitializers.voicePicker.initialized, tryInitVoicePicker);
}

if (document.readyState === 'loading') {
  document.addEventListener('DOMContentLoaded', start);
} else {
  start();
}
```

--------------------------------

### Project Setup and Dependency Installation

Source: https://docs.venice.ai/guides/projects/security-code-reviewer

Commands to create a new project directory, navigate into it, initialize dependencies using uv, and add essential Python packages for the security reviewer.

```shellscript
mkdir venice-security-reviewer
cd venice-security-security-reviewer
uv init
uv add "openai>=1.54" "pydantic>=2.9" "typer>=0.12"
```

--------------------------------

### Using Venice Parameters for Web Search

Source: https://docs.venice.ai/overview/getting-started

This example demonstrates how to enable Venice-specific features, such as automatic web search, by including `venice_parameters` in the `extra_body`. Ensure your VENICE_API_KEY is set.

```Python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("VENICE_API_KEY"),
    base_url="https://api.venice.ai/api/v1"
)

completion = client.chat.completions.create(
    model="zai-org-glm-5",
    messages=[
        {"role": "user", "content": "What are the latest developments in AI?"}
    ],
    extra_body={
        "venice_parameters": {
            "enable_web_search": "auto",
            "include_venice_system_prompt": True
        }
    }
)

print(completion.choices[0].message.content)

```

--------------------------------

### Printing the AI's Response in Node.js

Source: https://docs.venice.ai/overview/getting-started

This Node.js example shows how to print the content of the first message from the AI's completion choice. Ensure you have the completion object available.

```javascript
print(completion.choices[0].message.content)
```

--------------------------------

### Initialize LLM and Tools

Source: https://docs.venice.ai/guides/integrations/crewai

Set up your Language Model (LLM) and any necessary tools. This example uses OpenAI's GPT-4 and a basic search tool.

```python
from crewai import Agent, Task, Crew, Process
from crewai_tools import SerperDevTool

# Initialize your LLM of choice
# For example: from langchain_openai import ChatOpenAI
# llm = ChatOpenAI(model_name="gpt-4", temperature=0.7)

# Define your tools
search_tool = SerperDevTool()

# Define your agents
researcher = Agent(
  role='Senior Research Analyst',
  goal='Uncover cutting-edge developments in AI and technology',
  backstory="""You are an expert researcher with a keen eye for emerging trends and a knack for synthesizing complex information.""",
  verbose=True,
  allow_delegation=False,
  # llm=llm # Uncomment this line to use your specified LLM
)

# Define your tasks
research_task = Task(
  description='Identify and summarize the top 5 recent breakthroughs in AI-powered language models.',
  expected_output='A report detailing the top 5 breakthroughs with a brief explanation for each.',
  tools=[search_tool],
  agent=researcher
)

# Instantiate the crew
crew = Crew(
  agents=[researcher],
  tasks=[research_task],
  process=Process.sequential # Tasks will be executed in the order they are defined
)

# Execute the crew
result = crew.kickoff()

print("\n\n## Research Report")
print(result)
```

--------------------------------

### Python Code Reviewer Example

Source: https://docs.venice.ai/guides/projects/security-code-reviewer

This snippet demonstrates how to use the Security Code Reviewer in Python. It shows how to load environment variables, get a template, and render it with specific targets. Ensure you have the necessary libraries installed.

```python
chains = list[Chain]
dropped_chains: list[Chain] = None = None

# env = _build_env()
template = env.get_template("report.md.j2")
return template.render(
    target=str(target),
    scanned_at=datetime.now(UTC).strftime(

```

--------------------------------

### eth_chainId RPC Request Example

Source: https://docs.venice.ai/api-reference/endpoint/crypto/rpc

Example of a JSON-RPC request to get the current chain ID.

```json
{
  "method": "eth_chainId",
  "params": [],
  "id": 1
}
```

--------------------------------

### Create and Initialize Project Directory

Source: https://docs.venice.ai/guides/projects/private-research-agent

Use these commands to create a new project directory and initialize it with uv.

```bash
mkdir venice-research-agent
cd venice-research-agent
uv init
```

--------------------------------

### Run OpenClaw Onboarding Wizard

Source: https://docs.venice.ai/guides/integrations/openclaw-bot

Initiate the OpenClaw onboarding process to configure providers and settings.

```bash
openclaw onboard

```

--------------------------------

### Install CrewAI

Source: https://docs.venice.ai/guides/integrations/crewai

Install the CrewAI library using pip. This is the first step to start using CrewAI in your Python environment.

```python
pip install 'crewai[all]'
```

--------------------------------

### Customizing Response Behavior

Source: https://docs.venice.ai/overview/getting-started

Control model output using parameters like `temperature`, `max_tokens`, `top_p`, `frequency_penalty`, and `presence_penalty`. This example also disables the Venice system prompt.

```Python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("VENICE_API_KEY"),
    base_url="https://api.venice.ai/api/v1"
)

completion = client.chat.completions.create(
    model="zai-org-glm-5",
    messages=[
        {"role": "system", "content": "You are a creative storyteller"},
        {"role": "user", "content": "Tell me a creative story"}
    ],
    temperature=0.8,
    max_tokens=500,
    top_p=0.9,
    frequency_penalty=0.5,
    presence_penalty=0.5,
    extra_body={
        "venice_parameters": {
            "include_venice_system_prompt": False
        }
    }
)

print(completion.choices[0].message.content)

```

--------------------------------

### Basic GET Request Example

Source: https://docs.venice.ai/guides/getting-started/postman

Demonstrates a simple GET request to an endpoint. Replace 'YOUR_API_KEY' with your actual Venice AI API key.

```javascript
const url = 'https://api.venice.ai/v1/models';
const apiKey = 'YOUR_API_KEY';

fetch(url, {
  method: 'GET',
  headers: {
    'Authorization': `Bearer ${apiKey}`
  }
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));
```

--------------------------------

### Audio Queue Example

Source: https://docs.venice.ai/api-reference/endpoint/audio/queue

This example demonstrates how to queue an audio processing task. Ensure you have the necessary authentication and parameters set up.

```javascript
self.__next_f.push([1, "6c:I[448287,[\"/mintlify-assets/_next/static/chunks/de15d9642f7c974c.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/b664fc8bb1e7ab0d.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/d53146a6ec2c0f8b.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/07eb678ee01a9cdf.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/90079180db6f14a4.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/22830d1507750daf.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/247f8594ded6e6f1.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/7285fd2749e1c6b9.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/6fd3acb5d5a9a0e5.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/bdb898abfe5bae4d.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/2fc1f5c43394028e.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/f9a25eb960109996.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/df2c0206ea0c5bc8.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/50537af49df8455c.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/204e747b034398c6.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/13ebb4257dd3a545.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/2aa76abbbffea05d.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/2e73684f85fc5509.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/55341d0a0dea6975.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/190e2d29d3b2239b.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/24ea02e20ac4ff55.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/d31db8d969fc01f1.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/a85a2fe12c3f93ec.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/e945895a97de48c6.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/e92309faf83811de.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\"],"MDXContentController",1])
self.__next_f.push([1, "6c:I[448287,[\"/mintlify-assets/_next/static/chunks/de15d9642f7c974c.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/b664fc8bb1e7ab0d.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/d53146a6ec2c0f8b.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/07eb678ee01a9cdf.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/90079180db6f14a4.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/22830d1507750daf.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/247f8594ded6e6f1.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/7285fd2749e1c6b9.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/6fd3acb5d5a9a0e5.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/bdb898abfe5bae4d.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/2fc1f5c43394028e.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/f9a25eb960109996.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/df2c0206ea0c5bc8.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/50537af49df8455c.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/204e747b034398c6.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/13ebb4257dd3a545.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/2aa76abbbffea05d.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/2e73684f85fc5509.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/55341d0a0dea6975.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/190e2d29d3b2239b.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/24ea02e20ac4ff55.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/d31db8d969fc01f1.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/a85a2fe12c3f93ec.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/e945895a97de48c6.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\",\"/mintlify-assets/_next/static/chunks/e92309faf83811de.js?dpl=dpl_Ehge2uUAA7nucoXBNvpqaxr3NGx1\"],"default",1])
self.__next_f.push([1, "68:T38ef7,[]"])
```

--------------------------------

### Example RPC Request

Source: https://docs.venice.ai/api-reference/endpoint/crypto/rpc

Demonstrates a basic JSON-RPC request to get the Ethereum chain ID. Includes example request and response bodies, and relevant response headers.

```shell
curl https://api.venice.ai/api/v1/crypto/rpc/ethereum-mainnet \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "method": "eth_chainId",
    "params": [],
    "id": 1
  }'
```

```json
{ "jsonrpc": "2.0", "id": 1, "result": "0x1" }
```

--------------------------------

### Step-by-Step Guide: Video Studio

Source: https://docs.venice.ai/guides/media/reference-to-video

Provides instructions for using the Video Studio to generate videos. Covers model selection, image uploading, and prompt writing.

```text
1. Select the model
Go to venice.ai/video. In the Model Browser, select Grok Imagine R2V.
2. Upload reference images
Click References in the input toolbar (or use the + menu) to open the reference images panel. Upload 1–7 images of the characters, objects, or scenes you want in the video.
Each image is automatically tagged as @Image1, @Image2, etc. in the order you upload them (left to right).
3. Write your prompt
Describe the video you want.
```