FinalRun uses a bring-your-own-key (BYOK) model — it does not proxy AI requests through its own infrastructure. When you run a test, the CLI calls your chosen AI provider directly using the API key you supply. This gives you full visibility into token usage and billing, and lets you use whichever model tier your team has access to.Documentation Index
Fetch the complete documentation index at: https://docs.finalrun.app/llms.txt
Use this file to discover all available pages before exploring further.
Prefer managed AI without provisioning a provider account? See Cloud API Key for the FinalRun Cloud option.
Supported providers
| Provider prefix | Environment variable | Recommended model family |
|---|---|---|
google/... | GOOGLE_API_KEY | Gemini 3 family and above |
openai/... | OPENAI_API_KEY | GPT-5 family and above |
anthropic/... | ANTHROPIC_API_KEY | Claude Sonnet 4 / Opus 4 and above |
--model value or the model field in .finalrun/config.yaml.
Setting your API key
You can supply an API key in three ways:- .env file
- Shell environment
- --api-key flag
Add the key to a The file is read automatically on every run. See Managing environments and secrets for dotenv load order details.
.env file at your workspace root. This is the recommended approach for local development.Setting a default model
Add amodel field to .finalrun/config.yaml so you don’t need to pass --model on every command:
.finalrun/config.yaml
provider/model-name format. Examples: google/gemini-3-flash-preview, anthropic/claude-sonnet-4-6, openai/gpt-5.
Provider setup examples
Test runs consume AI provider tokens. Standard API billing from your provider applies — FinalRun does not add any markup or usage fees on top of provider costs.

