Anthropic Claude
Use Anthropic's Claude models as the AI provider for BDD and test case generation. Claude excels at long-context documents and produces nuanced, detailed Gherkin scenarios.
Get an API key
- Go to console.anthropic.com → API Keys → Create Key.
- Copy the key — it starts with
sk-ant-.
Configure in QA Hub
- Go to Settings → AI Model.
- Select Anthropic as the provider.
- Paste your API key.
- Select a model.
- Click Test connection, then Save.
Available models
| Model | Speed | Context | Best for |
|---|---|---|---|
claude-sonnet-4-6 | Fast | 200K tokens | Production workloads, best quality/cost ratio |
claude-haiku-4-5 | Very fast | 200K tokens | High-volume, cost-efficient generation |
claude-opus-4-7 | Slow | 200K tokens | Maximum quality for complex test suites |
Long-context advantage
Claude's 200K token context window allows QA Hub to include full specification documents, multiple Confluence pages, and rich acceptance criteria in a single generation call — resulting in more comprehensive and accurate test coverage than shorter-context models.
Pricing
Anthropic charges per million input/output tokens. Sonnet offers the best balance for typical QA Hub usage patterns.
Troubleshooting
| Error | Cause | Fix |
|---|---|---|
401 authentication_error | Invalid API key | Generate a new key |
529 overloaded_error | Anthropic service busy | Retry — treated as transient, no quota flag |
| Quota exhausted | Credit balance depleted | Top up account; QA Hub sets the quotaExhausted flag |