Urgent: Unexpected AI Credit Usage Issue

I'm seeing the same thing, when the app first free credits, it used a maximum of 12 credits per consultation.

After applying a full professional plan with 3000 credits, each consultation can now cost up to 200 credits ?¿?¿

i dont understand how it can be so disproportionate, some consultations have been completely wrong and required editing also… is this a marketing trick to burn out their subscribers later?

I don't get it; it seems a bit abusive and deceptive.

Hi everyone, Celine from the Figma Community here. Thanks for taking the time to share this, it's really helpful context.

Figma Make uses an agentic AI system, which means credit usage can vary based on factors like model selection, task complexity, and the amount of context provided.

On the higher credit usage you're seeing (like the 136 or 200 credits on a single prompt), a few key factors can impact this:
- Model selection: It's important to note that credit consumption may vary based on the model being used while prompting. More advanced models (like Claude Opus 4.60) are more powerful but they also consume more credits than the default model.
- Context materials: Providing additional context, such as attached files or design libraries, can help improve results but may also increase credit usage.
- Task complexity: More complex requests or prompts that require multiple steps will use more credits. Even shorter prompts can use more credits if the task involves broader changes across a large or intricate file.

Please also note that you can select the model for each prompt in Figma Make, giving you flexibility to manage credit usage based on your needs.

​@SKOUZ : Regarding the behavior you mentioned (e.g. fixes not applied or unrelated changes), that's definitely something we'd want to take a closer look at — especially if it's impacting both results and credit usage.
I saw that you have already reached out to the Support team, thanks for doing that! If you're able to share a specific example (prompt + result), along with the model used directly in your case, that would really help us investigate further.

Appreciate you raising this, it's valuable feedback for improving the experience.

Hi ​@Celine_ ,

thank you for your reply and for taking the time to explain the factors that can influence credit usage, this is appreciated.

To clarify our specific case:

Model selection: We have always used the recommended default model.
Context materials: None were provided (no attachments, libraries, or external files).
Task complexity: Extremely low - a simple prompt to change some label colors to black.

Brief scenario overview (see screenshots provided)

1. An error was introduced by the Agent itself after my simple prompt to change label colors (cost: 224 AI credits).
2. The Agent reasoned: “I see the issue! I accidentally removed the opening curly brace from the onChange prop. Let me fix that.”
3. The Agent attempted a fix and claimed success - however, the issue was not resolved.
4. The Agent continued reasoning, modifying multiple files (7 files, then 4 files), repeatedly stating that everything was fixed - which guess what - again was not the case.
5. Eventually, the Agent produced a working state - although later we discovered the fix was still incomplete.

Key concern

The root problem was introduced by the Agent itself, not by the original prompt.

In other words:

• A simple visual change request triggered a structural code issue
• The Agent attempted multiple self-repairs
• Additional prompts were required to fully resolve the situation

Overall, the correction process alone consumed an additional 200–300 AI credits, despite originating from an Agent-introduced error.

Why this is problematic

Compared to other AI tools we currently use, this level of consumption is exceptionally high.

Under the current logic, our Pro Plan allocation of 3,000 credits effectively translates to only about 20–30 prompts, which seems disproportionate for typical usage scenarios.

Even when extrapolating to higher-tier plans:

• Organization Plan: ~25–35 prompts (≈100 credits each)
• Enterprise Plan: ~33–43 prompts

This makes Figma Make AI approximately 10–15× more expensive than comparable tools for similar tasks, which is difficult to justify for ongoing production use.

Request for clarification

Could you please clarify what might cause such a spike in credit consumption under these specific conditions – particularly when:

• The default model is used
• No additional context is supplied
• The task itself is simple
• 2–3 months ago, AI credit consumption was much more consistent and transparent. Prompts typically triggered alerts such as: "Used 7 AI Credits" "Used 12 AI Credits" "Used 15 AI Credits" Occasionally, "No AI Credits were used"

Is there any mechanism in place to prevent excessive credit usage when the Agent is attempting to repair issues it introduced?

We genuinely see strong potential in Figma Make AI and would like to continue using it productively. However, the current cost-to-output ratio in scenarios like this raises concerns for sustainable adoption, especially at team scale.

Thank you again for your support and for looking into this matter.

Best regards,
Anton Elshani
SKOUZ, Germany

I’m experiencing the exact same issue and it’s honestly quite frustrating. The credit consumption for Make / AI tasks feels completely disconnected from the actual complexity of the work.

Just today, I had over 600 credits left. I prompted an adjustment to an existing design - a task that might cost a maximum of  200-300 credits based on my history. Not only did the AI fail to implement a single change, but it also wiped out my entire balance. I am now at 0 credits with zero output to show for it.

Charging users full price for failed iterations or simple corrections of mistakes the AI did - is not sustainable. There needs to be a refund logic or a “quality check” before credits are permanently deducted.

Thanks both for sharing these details, I hear your concerns around credit usage, let me clarify how this works.

On credit consumption: AI credits are based on the work Figma Make performs in response to a prompt (including follow-up prompts used to refine results). So even when iterating to correct outputs, credits will still be consumed accordingly if the system is performing actions.
(An "output" includes any work completed by the model such as generating or updating code, or making changes to your file). 
Please also note, if a prompt fully fails and no work is performed or no output is generated, credits aren't deducted.

Also, given the nature of generative AI, usage can vary depending on the situation. Even with the default model, results may sometimes be inaccurate, incomplete, or not behave as expected, and outputs can differ based on factors like the prompt or file context. However, credits will still be consumed if work was performed.

That said, the behavior you're describing is something we'd definitely want to investigate more closely.
For ​@SKOUZ:  since you already have an open support ticket, could you continue the conversation there? The support team is best equipped to review your specific case in detail.

For others experiencing similar issues — if you believe no work was performed or no output was generated, please reach out to our support team with a specific example (prompt + result) so our team can take a closer look at it. 

You can do this via the Support Hub → click Start a chat → type “Report a bug”, and include your impacted file by sharing it with support-share@figma.com with “Can View” access. This allows us to reproduce and investigate the issue.

Thank you again for raising this.

I am seeing the exact same thing - i have burned through all my credits just trying to correct what AI did wrong and the prompt was very specific.  For example, make had wrapped all my column headers in a table in one column and I had to use credits to repeatedly tell it what was wrong.  It took three tries to get it right, even when i sent in screenshots.  Another example is when make only gave me one person in a dropdown menu and Im on my 8th prompt trying to correct it to show multiple.  It seems like the credit usage should not be deducted if the prompt is accurate and the AI is wrong.

This appears to be classic drug dealer mentality. Get them hooked for free/cheap and once it’s in your work flow then that’s when the real costs are visible. I’m 100% sure that’s the mindset. 

Also, if the AI system is causing problems, as I have documented with Figma’s support team, then why so I have to pay to fix the problem that the AI caused to begin with?  If use a simple, similar prompt like “change the word fish to dog” then causes a 100+ credit cost in AI damage and then repair to what it broke, why am I responsible?

It charged me 62 credits to change 3 numbers and still took roughly 3 minutes. Most people could have changed it faster manually. 

I can’t tell you how many times I was charged when nothing changed at all. 

Lastly, no one can explain (or they simply ignore the question) why adding a seat, which is necessarily more expensive to Figma than adding more credits because it gives access to more tools to another person, is cheaper than the up to 5.6X cost off adding more credits… 

There are too many equivalent alternatives for Figma to change this to their business model and think it’s going to work long term. 

I deeply love Figma—it's always set itself apart as a shining beacon among design tools. It offers so much: an incredible array of features, a supportive and vibrant community, unmatched simplicity, seamless collaboration, and effortless integration. Working on projects in Figma feels like assembling the Avengers, a true team effort where everything falls into place with ease and excitement. But lately, my enthusiasm has been tinged with disappointment. The new AI limitations have cast a shadow over what once felt like boundless creativity. Yes, I understand the AI does what we ask—yet it’s never in one smooth go. Sometimes it hits, sometimes it misses—leaving us frustrated, and sadly, it’s draining all our AI credits. I believe most of us in the community yearn for increased AI limits, tailored to different plans, to truly unleash our potential. My heartfelt plea to Figma: please reconsider the AI credit model. Make it more fair, more considerate to the passionate creatives who rely on this tool. We are the minds that breathe life into ideas—don’t let limitations stifle our creativity.

I’m running into the same issue — I’ve already burned through a significant amount of credits just trying to fix mistakes made by the AI.

What’s more concerning is the inconsistency in credit usage. Right after a response, it shows something like 30, 58, or 60 credits consumed. But when I check the credit usage from the billing section, the total consumption is much higher than what was initially displayed.

It feels like additional credits are being deducted behind the scenes, which isn’t clearly reflected upfront.

Is there any option to set credit usage limit alert, I didn’t find any such option

Hey All, thank you for chiming in here! 
 

I hear your frustration, especially around visibility into credit usage and not having alerts to track it in real time. That’s valid feedback, and I can see why that would be helpful for managing usage more confidently.

To clarify again how credits work today:

AI credits are based on the work Figma Make performs in response to a prompt, including any follow-up prompts used to refine results. So even when you're iterating to fix or improve an output, credits are still consumed if the system is performing actions (for example, generating or updating code, or making changes to your file).

If a prompt fully fails and no work is performed, meaning no output is generated; then, credits are not deducted.

Because this is generative AI, usage can vary depending on the situation. Even when using the same model, outputs may be incomplete or not behave as expected, and results can differ based on things like your prompt or file context. Credits will still be consumed in cases where work was performed, even if the result wasn’t what you intended.

To address ​@Runo Tech’s request to set credit usage limit alerts, there isn’t currently a way to set up alerts, but I hear the need for that clearly in this thread. We’ll pass this onto the team for future consideration. 

That said, the behavior some of you are describing is something we’d want to take a closer look at.

• If you already have an open support ticket, please continue working directly with the support team via email. They’re best equipped to dig into your specific case.
• If you’re seeing this and believe credits were used when no work was performed or no output was generated, please reach out with a specific example (prompt + result), so the support team can investigate with you.

Again, you can contact support via the Support Hub → click Start a chat → type “Report a bug,” and share your impacted file with support-share@figma.com (set to “Can View”), so the team can try to reproduce the issue. Thank you all again for raising your concerns. It’s very helpful for the team to understand where things aren’t meeting expectations.

Well. It seems that my issue is all yours as well… I had also high consumption on AI Credits and in 5 days, all my AI credits were gone. Purchased 1000 more. Less than a day to finish. Probably I do need to learn how to better manage credit usage through efficient use of Figma but this kind of surprise is a bit disappointing once I am now unable to continue my projects without add more credit. I know that the goal probably is to enhance environment and maybe have a better cost management from FIGMA over AI resources but as mentioned above, the new AI limitations have cast a shadow over what once felt like boundless creativity. FIGMA helped me a lot in a bunch of projects however it seems to be time to find another solution which can compete with FIGMA...