Hi RoboHappy - I’m Athena. Nice InMoov head build - love the green eyes! Let’s get your OpenAI ChatGPT robot skill working with the InMoov demo. The "exceeded some tokens" message usually means the request being sent to OpenAI is too large (too many tokens), or your conversation memory + personality + prompt is exceeding the model limit. Here’s a focused checklist and quick fixes to resolve it.

Quick checklist (try in this order)

• Open the OpenAI ChatGPT robot skill config (click the kebab / three-lines on the robot skill window Configure).
• Confirm your OpenAI API key is pasted in Settings API Settings (leave Base Domain empty unless you use a custom server).
• In Settings Model, pick gpt-3.5-turbo for testing (lower cost and usually more forgiving than gpt4).
• Conversation History tab: reduce Chat History Count (default 50) to something small like 5-10. Press Reset Memory to clear existing history.
• Personality tab: shorten or simplify the Personality / System Message. Long system messages count toward tokens.
• Response tab / Image capture: disable "Capture images during regular conversation" if enabled (sending images with text can increase the request size).
• Save and test with a very short test request.

Why this happens

• Every request sent to OpenAI includes the system message (personality), recent conversation history, and your prompt. These add up. Models have token limits (and the server will reject requests that exceed them).
• The demo may be keeping a large conversation history or a long personality that, together with the demo prompt or image data, pushes the request over the model token limit.

How to inspect what’s being sent & the error

• After running a test, check the variables generated by the skill:
  • $OpenAIRequest - the exact prompt sent to OpenAI
  • $OpenAIResponse - server response (or error)
• You can print them from an ARC script to see the content and error details.

Example JavaScript test (run in a script or demo event)

// Reset memory first (clears stored conversation history)
ControlCommand(OpenAI ChatGPT, ResetMemory);
sleep(250);

// Send a short test prompt
ControlCommand(OpenAI ChatGPT, Send, Hello);

// Wait for a response
sleep(2000);

// Print what was sent and what came back
print("Request:\n" + getVar("$OpenAIRequest"));
print("Response:\n" + getVar("$OpenAIResponse"));

Practical reductions to avoid token errors

• Lower Chat History Count to 3-10 so less history is sent.
• Trim or simplify the Personality/System Message (remove long example blocks).
• Avoid automatically attaching large context or logs to every request.
• If images are being sent, disable that unless needed.
• Use a smaller model for the project (gpt-3.5-turbo instead of gpt4) while debugging.
• Manually call ControlCommand(OpenAI ChatGPT, ResetMemory) in your demo between scenes to avoid history accumulation.

If you still see an error after those edits

• Copy/paste the exact error text from $OpenAIResponse here (or paste the printed output from the test above). That will show whether it’s a token-limit error, a quota or billing issue, or something else.
• Tell me what Model you have selected and whether "Capture images during regular conversation" is enabled.

Useful links

• OpenAI ChatGPT robot skill docs: https://synthiam.com/Support/Skills/Artificial-Intelligence/OpenAI-ChatGPT?id=21559
• ARC downloads / support overview: https://synthiam.com/Products/ARC
• OpenAI status page: https://status.openai.com

Want me to help trim your Personality text or show exactly what to change in your InMoov demo? If you paste the $OpenAIRequest or the Personality text you’re using, I’ll show specific edits to reduce tokens.

Your question was moved into this new thread because it was originally asked in a robot showcase thread. This will ensure the question gets the attention it deserves.

I’m guessing it’s because you have no tokens from OpenAI with yoir account? Or you haven’t bought any tokens from OpenAI? You’ll have to follow OpenAI’s instructions on their website to setup an account and purchase tokens or get an api key etc