​
Step-by-step guide

To get started with Venice quickly, you’ll need to:

1

Generate an API Key

Navigate to your user settings within your Venice API Settings and generate a new API key.

For a more detailed guide, check out the API Key page.

2

Choose a model

Go to the “List Models” API reference page and enter your API key to output a list of all models, or use the following command in a terminal

# Open a terminal, replace <your-api-key> with your actual API key, and run the following command
curl --request GET \
  --url https://api.venice.ai/api/v1/models \
  --header 'Authorization: Bearer <your-api-key>'
3

Text Prompt

Go to the “Chat Completions” API reference page and enter your API key as well as text prompt configuration options, or modify the command below in a terminal

# Open a terminal, replace <your-api-key> with your actual API key, edit the information to your needs and run the following command
curl --request POST \
--url https://api.venice.ai/api/v1/chat/completions \
--header 'Authorization: Bearer <your-api-key>' \
--header 'Content-Type: application/json' \
--data '{
 "model": "llama-3.3-70b",
 "messages": [
  {
   "role": "system",
   "content": "You are a helpful assistant"
  },
  {
   "role": "user",
   "content": "Tell me about AI"
  }
 ],
 "venice_parameters": {
  "enable_web_search": "on",
  "include_venice_system_prompt": true
 },
 "frequency_penalty": 0,
 "presence_penalty": 0,
 "max_tokens": 1000,
 "max_completion_tokens": 998,
 "temperature": 1,
 "top_p": 0.1,
 "stream": false
}'
4

Image Generation

Go to the “Generate Images” API reference page and enter your API key as well as image prompt configuration options, or modify the command below in a terminal

# Open a terminal, replace <your-api-key> with your actual API key, edit the information to your needs and run the following command
curl --request POST \
--url https://api.venice.ai/api/v1/image/generate \
--header 'Authorization: Bearer <your-api-key>' \
--header 'Content-Type: application/json' \
--data '{
"model": "fluently-xl",
"prompt": "A beautiful sunset over a mountain range",
"negative_prompt": "Clouds, Rain, Snow",
"style_preset": "3D Model",
"height": 1024,
"width": 1024,
"steps": 30,
"cfg_scale": 7.5,
"seed": 123456789,
"lora_strength": 50,
"safe_mode": false,
"return_binary": false,
"hide_watermark": false
}'

​
Step-by-step guide

To get started with Venice quickly, you’ll need to:

1

Generate an API Key

Navigate to your user settings within your Venice API Settings and generate a new API key.

For a more detailed guide, check out the API Key page.

2

Choose a model

Go to the “List Models” API reference page and enter your API key to output a list of all models, or use the following command in a terminal

# Open a terminal, replace <your-api-key> with your actual API key, and run the following command
curl --request GET \
  --url https://api.venice.ai/api/v1/models \
  --header 'Authorization: Bearer <your-api-key>'
3

Text Prompt

Go to the “Chat Completions” API reference page and enter your API key as well as text prompt configuration options, or modify the command below in a terminal

# Open a terminal, replace <your-api-key> with your actual API key, edit the information to your needs and run the following command
curl --request POST \
--url https://api.venice.ai/api/v1/chat/completions \
--header 'Authorization: Bearer <your-api-key>' \
--header 'Content-Type: application/json' \
--data '{
 "model": "llama-3.3-70b",
 "messages": [
  {
   "role": "system",
   "content": "You are a helpful assistant"
  },
  {
   "role": "user",
   "content": "Tell me about AI"
  }
 ],
 "venice_parameters": {
  "enable_web_search": "on",
  "include_venice_system_prompt": true
 },
 "frequency_penalty": 0,
 "presence_penalty": 0,
 "max_tokens": 1000,
 "max_completion_tokens": 998,
 "temperature": 1,
 "top_p": 0.1,
 "stream": false
}'
4

Image Generation

Go to the “Generate Images” API reference page and enter your API key as well as image prompt configuration options, or modify the command below in a terminal

# Open a terminal, replace <your-api-key> with your actual API key, edit the information to your needs and run the following command
curl --request POST \
--url https://api.venice.ai/api/v1/image/generate \
--header 'Authorization: Bearer <your-api-key>' \
--header 'Content-Type: application/json' \
--data '{
"model": "fluently-xl",
"prompt": "A beautiful sunset over a mountain range",
"negative_prompt": "Clouds, Rain, Snow",
"style_preset": "3D Model",
"height": 1024,
"width": 1024,
"steps": 30,
"cfg_scale": 7.5,
"seed": 123456789,
"lora_strength": 50,
"safe_mode": false,
"return_binary": false,
"hide_watermark": false
}'