Venice supports additional capabilities within it’s models that can be powered by the venice_parameters input on the chat completions endpoint.

In certain circumstances, you may be using a client that does not let you modify the request body. For those platforms, you can utilize Venice’s Model Feature Suffix offering to pass flags in via the model ID.

Instructions

You can append any valid venice_parameter value to the end of the model ID as follows. These feature suffix should follow the model name with a : and you can chain multiple features together:

To Set Web Search to Auto

default:enable_web_search=auto

To Enable Web Search and Disable System Prompt

default:enable_web_search=on&include_venice_system_prompt=false

To Enable Web Search and Add Citations to the Response

default:enable_web_search=on&enable_web_citations=true

To Use a Character

default:character_slug=alan-watts

To Hide Thinking Blocks on a Reasoning Model Response

qwen3-4b:strip_thinking_response=true

To Disable Thinking on Supported Reasoning Models

Certain reasoning models (like Qwen 3) support disabling the thinking process. You can activate using the suffix below:

qwen3-4b:disable_thinking=true

Postman Example

You can view an example of this feature in our Postman Collection here.