Google Gemini
Google Gemini is the recommended AI provider for most QA Hub deployments. It offers a generous free tier, fast response times, and strong performance on structured test generation tasks.
Get an API key
- Go to aistudio.google.com → Get API key.
- Create a new key or use an existing one.
- Copy the key — it starts with
AIza.
Configure in QA Hub
- Go to Settings → AI Model.
- Select Google Gemini as the provider.
- Paste your API key.
- Select a model (see below).
- Click Test connection, then Save.
Available models
| Model | Speed | Context | Best for |
|---|---|---|---|
gemini-2.0-flash | Fast | 1M tokens | High-volume generation, default choice |
gemini-2.5-pro | Slower | 2M tokens | Complex acceptance criteria, nuanced output |
gemini-1.5-pro | Medium | 2M tokens | Stable production workloads |
Thinking mode
Gemini 2.5 Pro supports extended thinking, which improves output quality for complex scenarios at the cost of higher latency and token usage. Disable it in Settings if speed is a priority:
Settings → AI Model → Disable thinking mode (Gemini)
Free tier limits
The Gemini free tier allows up to 1,500 requests per day and 1M tokens per minute on Flash models. For teams generating more than ~200 test cases per day, a paid plan is recommended.
Troubleshooting
| Error | Cause | Fix |
|---|---|---|
429 RESOURCE_EXHAUSTED | Daily quota hit | Wait until reset or upgrade plan |
403 API_KEY_INVALID | Wrong or revoked key | Generate a new key in AI Studio |
503 overloaded | Temporary Google outage | Retry — QA Hub does not set quota flag for this |