Foglamp prices every span at ingest, the moment it arrives, from the token dimensions the provider reported. Cost is never recomputed downstream, so what you see in a trace is what was charged when it landed.Documentation Index
Fetch the complete documentation index at: https://docs.foglamp.dev/llms.txt
Use this file to discover all available pages before exploring further.
How pricing works
Each usage dimension is priced independently against a model price table sourced from OpenRouter, refreshed every 24 hours. The dimensions priced are prompt, completion, request, image, web-search, internal reasoning, cache-read, and cache-write tokens. The span detail panel shows a pricing source so you can see whether a cost came from the resolved OpenRouter price or one of your custom rules.A model Foglamp can’t find a price for is labelled
(unknown) in cost
breakdowns — never silently treated as $0. The Overview KPI’s ”% priced”
tells you what fraction of LLM spans were priced; a low number usually means
you’re running a model that needs a custom rule.Custom pricing rules
Use the Pricing page to override or supply prices — for a self-hosted model, a negotiated rate, or a model OpenRouter doesn’t list. A rule has a model pattern (e.g.openai/gpt-4o-mini) and one or more price
dimensions. The two most common — prompt price and completion price —
are in the create dialog; the full set of eight dimensions (request, image,
web-search, reasoning, cache-read, cache-write) is supported by the API.
- Any dimension you set on a rule wins over the OpenRouter price.
- Any dimension you leave unset falls back to the resolved OpenRouter price.
- An optional effective-from date lets a rule apply only to spans after a cutoff, so historical costs stay correct when a price changes.