Supported Answer Models
The
openai/gpt-5.1 backend mapping is intentionally left for your later backend update.Provider Keys
provider_key is accepted for backward compatibility but currently ignored; provider usage is not billed to the user’s provider account.
Use LLMLayer response fields and the dashboard ledger as the billing source of truth.
Answer Pricing
LLMLayer flat-price models
Token-priced models
Utility Endpoint Pricing
Cost Control
- Start Answer requests with
llmlayer-webandmax_queries=1. - Use Web Search + Scraper when you need to select sources before asking an LLM.
- Use Extract only for fields you actually need.
- Request one scrape format unless you need multiple outputs.
- Read
cost,llmlayer_cost, andmodel_costfrom responses when present.
FAQ
Can I bring my own provider API key?
Can I bring my own provider API key?
provider_key is accepted for backward compatibility but currently ignored; provider usage is not billed to the user’s provider account.What happens if I pass an unsupported model?
What happens if I pass an unsupported model?
The Answer backend currently falls back to
llmlayer-web rather than failing the request.Where should I verify final charges?
Where should I verify final charges?
Use the response cost fields for request-level visibility and the dashboard ledger as the account-level billing source of truth.
Next Steps
Answer API
Model selection, streaming, and response fields.
Errors & Refunds
Error shapes, status codes, and refund behavior.