Return a monthly cost estimate for a prospective provider choice.
Uses the standard assumption documented on
pragma_sdk.models.llm.CostEstimate: 10,000 platform agent
invocations per month averaging 2,000 input and 500 output tokens.
The response includes a provider comparison table so the settings
UI can render a side-by-side cost breakdown before the user
commits to a selection.
Returns: Cost estimate with per-call, monthly, and comparison data.
Provider slug to estimate.
Performance profile tier to estimate.
fast, balanced, reasoning Successful Response
Cost projection for a proposed LLM provider and performance profile.
Returned by the settings cost preview endpoint so the UI can show a live comparison before the user commits to a change. The standard assumption used for the projection is 10,000 platform-agent invocations per month with an average of 2,000 input tokens and 500 output tokens per invocation; the API applies this assumption uniformly across providers so the comparison is apples-to-apples.
Attributes: provider: Provider slug the estimate targets. performance_profile: Profile tier the estimate targets. monthly_estimate_usd: Projected monthly cost in USD at the standard assumption. per_call_estimate_usd: Projected cost per platform-agent invocation in USD at the standard assumption. provider_comparison: Alternative provider/profile combinations and their monthly cost estimates, for side-by-side display.
User-facing LLM performance profile selection.
Identifies which tier of model an organization wants platform agents to use. The profile is chosen by the user; the API resolves it to a concrete model from the selected provider's catalog entries.
fast, balanced, reasoning ^(?!^[-+.]*$)[+-]?0*\d*\.?\d*$^(?!^[-+.]*$)[+-]?0*\d*\.?\d*$