Brushless Motor Movement Panel icon Brushless Motor Movement Panel — Control brushless motor controllers (hoverboard-style) via EZ-B: configure direction, speed and optional brake ports for DIY robot movement. Try it →
Australia
Asked
Resolved Resolved by Synthiam Support!
Openai Reasoning Parameter In Arc

Openai Reasoning Parameter In Arc

,

Using the OpenAI ChatGPT robot skill in ARC, how do I invoke the "reasoning" parameter to speed up response time? I want to set GPT-5_Nano's reasoning to minimal. Am I expected to set this in the skill's settings or via ARC scripting (JavaScript/Python)?

Sample code might look like:

reasoning = {"effort": "minimal"}


Related Hardware (view all EZB hardware)
EZ-B V4 by EZ-Robot
EZ-B v4 with Synthiam ARCx controls servos, sensors, camera and audio over Wi-Fi or USB serial, no firmware needed.
Wi-Fi / USB
Servos 24
Camera
Audio
UART 3
I2C
ADC 8
Digital 24

Related Robot Skill (view all robot skills)
Chatbot robot skill for human-like conversation, memory, image description, personality control, and scriptable AI actions in ARC

ARC Pro

Upgrade to ARC Pro

Unlock the true power of automation and robotics by becoming a proud subscriber of Synthiam ARC Pro.

Author Avatar
PRO
Canada
Twitter YouTube GitHub
#1  

In ARC’s OpenAI ChatGPT Robot Skill, you don’t set the OpenAI reasoning parameter through ARC scripting. That skill is designed to use its Settings and Personality tabs, but it does not expose a custom raw JSON request body like:

{"reasoning":{"effort":"minimal"}}

What that means

  • Not via JavaScript/Python in ARC
  • Not as a script variable
  • Only if the robot skill itself adds support for that model option

If the skill’s UI doesn’t already include a reasoning effort or similar option, then ARC can’t pass it through directly. In that case, the proven path is to:

  1. Open the OpenAI ChatGPT Robot Skill
  2. Click the kebab menu on the skill
  3. Check Settings / Personality for any model-specific options
  4. If there’s no reasoning control there, the skill simply isn’t exposing it yet

Important note

GPT-5_nano and the reasoning.effort parameter are model/API-specific settings. ARC’s OpenAI skill may not currently support passing arbitrary OpenAI request fields unless Synthiam adds that option to the skill.

Best way forward

If you need full control over OpenAI request JSON, the better solution is to create a custom robot skill that calls the OpenAI API directly from JavaScript or Python. That lets you send whatever payload the API supports.

Synthiam’s guide for that is here:
https://synthiam.com/Support/Create-Robot-Skill/Overview

Example direction for a custom skill

In a custom skill, you could build the request body yourself and POST it with Net.hTTPPost().

If you want, I can help you with a JavaScript custom skill example that sends reasoning: { effort: "minimal" } to OpenAI.

Also, what are you trying to optimize overall - fast conversational replies, cheaper API usage, or best answer quality with less latency?

I am a customer support AI and still learning. Please verify important answers in our support documentation. For advanced AI features, use the AI Script Agent built into ARC.
Author Avatar
PRO
Australia
#2  

Thanks for the info. I am trying to achieve a response time equivalent to the recently decommissioned gpt-4-nano. Gpt-5-nano is far too slow to be of any use. For example, 7 secs to describe an image, whereas gpt-4-nano was 1 sec. As for having a conversation, response time is 30 secs. using gpt-5. By default gpt-5-nano sets the reasoning effort to medium, hence the high latency.

#3  

We will take a look to see what parameters are exposed. Be aware that not all parameters are supported by all models. And sometimes the only way to find out is by trying and receiving errors or unusable responses.

Author Avatar
PRO
Australia
#4  

Thanks for looking into this. It is an example of ChatGPT OpenAI developers thinking they are improving a service whereas in fact making it worse. If they had kept gpt-4, I would be happy.

Author Avatar
PRO
Australia
#6  

Tested and working. Using the LOW setting, response times were back to gpt-4 response times - about 1 sec for image description. Also I think the responses are more natural than with the MEDIUM setting. Thanks again.

📚 This thread has been preserved as a helpful resource!

While new comments are no longer being accepted, the information here remains available for learning and reference. Check the most recent comment for additional details.