Skip to content

Add pricing faq for PostHog AI credits #13524

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
annikaschmid wants to merge 19 commits into from
Closed

Add pricing faq for PostHog AI credits #13524

Changes from 1 commit
Commits
Show all changes
19 commits
Select commit Hold shift + click to select a range
714f8c7
add pricing faq for PostHog AI credits
annikaschmid Nov 4, 2025
b9076cc
updates based on feedback
annikaschmid Nov 12, 2025
d27eecf
Fix typos
Nov 12, 2025
beb4b97
No bolds on headings
gewenyu99 Nov 13, 2025
29f875e
Update contents/docs/posthog-ai/pricing-faq.mdx
annikaschmid Nov 17, 2025
f4e5e90
Update contents/docs/posthog-ai/pricing-faq.mdx
annikaschmid Nov 17, 2025
bf71624
Update contents/docs/posthog-ai/pricing-faq.mdx
annikaschmid Nov 17, 2025
0a5bf0a
Update contents/docs/posthog-ai/pricing-faq.mdx
annikaschmid Nov 17, 2025
62dafd9
Update contents/docs/posthog-ai/pricing-faq.mdx
annikaschmid Nov 17, 2025
2223048
Update contents/docs/posthog-ai/pricing-faq.mdx
annikaschmid Nov 17, 2025
0c913b6
Update contents/docs/posthog-ai/pricing-faq.mdx
annikaschmid Nov 17, 2025
9ff220f
Update contents/docs/posthog-ai/pricing-faq.mdx
annikaschmid Nov 17, 2025
e97c4fe
Update contents/docs/posthog-ai/pricing-faq.mdx
annikaschmid Nov 17, 2025
5b3ea75
Update contents/docs/posthog-ai/pricing-faq.mdx
annikaschmid Nov 17, 2025
661257d
Update contents/docs/posthog-ai/pricing-faq.mdx
annikaschmid Nov 17, 2025
5e79e52
Update contents/docs/posthog-ai/pricing-faq.mdx
annikaschmid Nov 17, 2025
15e29cb
Update contents/docs/posthog-ai/pricing-faq.mdx
annikaschmid Nov 17, 2025
8f6d698
Update contents/docs/posthog-ai/pricing-faq.mdx
annikaschmid Nov 17, 2025
0b45ef4
Update contents/docs/posthog-ai/pricing-faq.mdx
gewenyu99 Nov 17, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
62 changes: 62 additions & 0 deletions contents/docs/posthog-ai/pricing-faq.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,62 @@
# PostHog AI credits

PostHog uses **AI credits** to charge for all of its AI features.
Each time you interact with an AI-powered feature — like asking PostHog to write SQL, summarize data, or analyze sessions — a small number of credits are used based on the complexity of your request.

This means you only pay for what you actually use.
There’s no fixed subscription — and every organization has a free tier worth $25 (2,500 credits) so you can explore all PostHog’s AI features before paying anything.

### **When AI credits are used**

AI credits are consumed whenever PostHog performs intelligent work for you.
You’ll spot these features by the ✨ icon or when using the in-app chat.
Comment on lines +7 to +8
Copy link
Contributor

@gewenyu99 gewenyu99 Nov 13, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
AI credits are consumed whenever PostHog performs intelligent work for you.
You’ll spot these features by the ✨ icon or when using the in-app chat.
AI credits are consumed whenever PostHog performs intelligent work for you. You’ll spot these features by the ✨ icon or when using the in-app chat.

@edwinyjlim maybe we rebase this on your other PR and link to the list of actions here (if we have a list)


Examples include:
- Searching for session recordings in natural language
- Summarizing experiment results
- Writing or debugging SQL with AI

### **What doesn’t use credits**

Getting help on how to use PostHog never costs credits.
Copy link
Member

@Twixes Twixes Nov 6, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I don't think this is strictly true, i.e. if you getting help involves a query being created – that costs credits.

Because we have a (we could say generous) free tier, is it perhaps then simpler – for both the user an us – to charge for the root node always? Regardless of whether just the docs search tool was involved, insight creation, or no tools at all. Especially with the new agent orchestration based on mode-switching, being prototyped by @skoob13, the tools become "dumb", and it's even trickier to say "this is just getting help" vs. "this is doing some work for the user".

Copy link
Contributor

@tatoalo tatoalo Nov 6, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yeah, completely agree @Twixes. We either are fully transparent on what we pass along to end user cost-wise or might as well remove this.
The current plan is to always charge for the root node anyway. Another (small) example is the title generator, we use a super small (i.e. fast) model to perform this simple operation, but we do still plan to pass that along to end user cost-wise. I would rather have a section explaining what we bill and what not, if not too technical and prone to being outdated (although we could work around that)

Copy link
Contributor Author

@annikaschmid annikaschmid Nov 17, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The outcome of this discussion is that we've updated the calculation and will not charge for the root node when a user searches the docs.

All AI features still in beta are also free to use — as of **Oct 31**, that includes **session summaries** and **deep research**.
Copy link
Contributor

@greptile-apps greptile-apps bot Nov 13, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

style: Add year to date for clarity (assuming 2024)

Prompt To Fix With AI 
This is a comment left during a code review.
Path: contents/docs/posthog-ai/pricing-faq.mdx
Line: 22:22

Comment:
**style:** Add year to date for clarity (assuming 2024)

How can I resolve this? If you propose a fix, please make it concise.


### **How credit usage works**
Copy link
Contributor

@patricio-posthog patricio-posthog Nov 4, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think this section is confusing. As a customer I read everything but still don't understand the relationship between tokens and credits. If we can't be fully transparent here, I would remove any references to tokens.

Copy link
Member

@edwinyjlim edwinyjlim Nov 4, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I agree this brings up questions like "well, why aren't they just charging me by tokens then?"

That being said, I think this section is important to have. It just needs more detail and reasoning and ideally a conversion calculator or formula. I'm assuming we're charging a slight markup or something!

Copy link
Member

@edwinyjlim edwinyjlim Nov 4, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Also, what about input tokens vs output tokens? and tokens between different LLM models? This section probably needs an in-depth breakdown of a few different prompts and tasks.

Copy link
Member

@Twixes Twixes Nov 6, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

If we clarify the set markup, like @kappa90 points out on line 35, I think this becomes fairly clear and user-friendly:

AI credits are based on the underlying token costs. The choice of model is optimized automatically per PostHog AI feature, but in each case our markup is a constant 20% over the LLM provider price. This means that 1 PostHog AI credit = $0.8333 worth of raw inference.

Note that 25% markup would be a pleasant $0.8.

Copy link
Contributor Author

@annikaschmid annikaschmid Nov 12, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Clarified in the relevant section below


AI credits are based on **token costs**, which reflect the effort required to complete your request.
Copy link
Contributor

@pawel-cebula pawel-cebula Nov 6, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Maybe "inference costs" instead of "token costs"? Addresses some concerns raised in comments above + feels more accurate since IIRC some model providers have pricing components that are not purely token based


- Simple queries (like “What were my daily active users in October?”) use very few tokens, and therefore very few credits.
- More complex tasks (like analyzing hundreds of session recordings or rewriting a SQL query multiple times) use more tokens and cost a bit more.

While exact usage varies, credit consumption usually scales with value — more advanced tasks cost more but deliver deeper insights and time savings.

You’ll always see **real-time cost information** while using AI features.
Copy link
Contributor

@pawel-cebula pawel-cebula Nov 6, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Will this real-time cost information include markup?

Copy link
Contributor Author

@annikaschmid annikaschmid Nov 12, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

yes 👍


To keep it simple, token costs are converted into **AI credits**, billed at **$0.01 per credit** — so **1,000 credits = $10**.
Copy link
Contributor

@kappa90 kappa90 Nov 5, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This hides the markup calculation. We should be clear that we take the token cost given us by the provider, apply a markup and convert to credits.

Copy link
Contributor Author

@annikaschmid annikaschmid Nov 12, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Clarified this

Copy link
Contributor

@kappa90 kappa90 Nov 13, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think we still don't mention the markup?


| Example interaction | Estimated credit cost |
| --- | --- |
| “What are my daily active users in October?” | coming soon |
| “Show me session recordings for this organization_id” | coming soon |
| “Can you help me write a SQL query that…” | coming soon |

---

### **Track your AI credit usage**

Stay on top of your AI credit spend in real time:

1. Type `/usage` in chat to see the current cost of your conversation
2. Check the **Billing & usage** page to view your total monthly consumption
Copy link
Contributor

@pawel-cebula pawel-cebula Nov 6, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

add links

3. (Coming soon) A dashboard showing which AI features use the most credits

> 💡 Credit data may take up to 24 hours to appear on the Billing & usage page.

---

### **Control your AI credit spend**

You’re always in control of your AI credit usage:
- **Real-time tracking** — see costs as you go
- **Billing limits** — set hard caps to prevent overspending
Copy link
Contributor

@pawel-cebula pawel-cebula Nov 6, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Mention the default paid limit? Assuming we're going with it

- **Usage alerts** — get notified when you hit key thresholds
Copy link
Contributor

@pawel-cebula pawel-cebula Nov 6, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Are these the standard billing alerts when you hit 80% and 100% of your free allowance (if on free plan) or billing limit (if on paid plan)? Or something custom for AI?

Copy link
Contributor Author

@annikaschmid annikaschmid Nov 12, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes, standard. We don't have anything custom planned for now