If you’re using OpenAI GPT-5.x or Google Gemini 3 with your own API keys in Heptabase, and you keep seeing a "Something went wrong, please try again later or contact support." message, this guide walks you through the most common causes and how to fix them.
Common symptoms
You may be affected if:
Your OpenAI or Gemini API key shows “Verified” in Heptabase, but:
GPT-5 models always fail with a generic error, or
Gemini 3 Pro always fails with a generic error
Gemini 2.5 works, but Gemini 3 does not
You've subscribed to ChatGPT Plus or Gemini Pro, and you can use ChatGPT 5.1 or Gemini 3 in their web UIs, but Heptabase AI Chat still fails when using those models.
If this sounds familiar, continue with the checks below.
Possible causes
These issues are usually caused by one or more of the following:
OpenAI organization not fully verified
OpenAI requires your organization (even for personal accounts) to complete identity verification before using GPT-5.x via API.Gemini API project billing not set up or on a limited tier
Having a Google AI Pro or similar subscription for the UI is not enough. The API project behind your Gemini key must have billing enabled and sufficient tier access for Gemini 3.Model-specific limitations or instability
Newer models (especially Gemini 3) may be more unstable or restricted than Gemini 2.5.
How to fix the issue
1. Check your OpenAI organization verification (for GPT-5.x)
If GPT-5 models fail but your API key is marked as verified in Heptabase:
Go to the OpenAI Platform
Open Settings → Organization → General → Verifications
Verify your organization to access protected models
If you’re asked to verify:
Follow the steps shown on the OpenAI platform (they may use a third-party service for identity verification).
After completing verification, wait a bit and then try GPT-5 again in Heptabase.
✅ If your organization is fully verified and billing is active, GPT-5 should usually start working without changing your API key.
2. Check your Gemini API billing and tier (for Gemini 3)
If:
Gemini 2.5 works
Gemini 3 Pro does not, even though you have a paid Google AI plan
then the problem is usually with the API project, not your subscription.
Open Google AI Studio
Visit:
https://aistudio.google.com/
Check your API key settings
Go to the API keys section.
Confirm that the key you pasted into Heptabase:
Belongs to the correct project you intend to use, and
Is active (not deleted or disabled).
Confirm billing is set up for the API project
Ensure the project connected to that API key has a billing account attached.
If you just created the project, you may need to finish the billing setup before Gemini 3 can be used.
Check your usage tier / quotas
Look for your tier level (for example, Tier 1 or higher).
If you’re only on a free or limited tier, Gemini 3 Pro may not be available, even if Gemini 2.5 works.
Try again in Heptabase
Re-paste the Gemini API key in Heptabase if needed.
Test:
A query with Gemini 2.5 (to confirm the key is valid).
Then a query with Gemini 3 Pro.
💡 If Gemini 2.5 works but Gemini 3 still fails after billing is correctly set up, we recommend using Gemini 2.5 as your main model, as it’s currently more stable.
When to contact Support
If you’ve:
Verified your OpenAI organization (or confirmed that it’s verified),
Set up billing and correct tiers for your Gemini API project,
Re-added your API keys, and
Still see “Something went wrong, please try again later or contact support.” when using GPT-5 or Gemini 3,
please contact our support team.
To help us help you faster, include:
Which model you were using.
What works and what doesn’t:
For example: “Gemini 2.5 works, but Gemini 3 fails,” or “Some random questions work, but asking it to summarize a PDF fails.”
A screenshot of:
The error message in Heptabase.
The relevant settings page from OpenAI or Google AI Studio.
Our team will look into your issue and help you get it resolved!
