LlamaIndex
Vitna reads 1 page from LlamaIndex every hour and prices 4 of its products in 1 market.
4 products priced · 1 market · 1 page read · newest confirmation
Every marketEvery providerHow the collector readsllamaindex.ai ↗
What LlamaIndex sells that the record prices
| Product | Figures | Read | Source |
|---|---|---|---|
| LlamaParse FastAny page, text only, no model in the loop | text from a page $0.0015 per page | confirmed 22 Nov 14:08 UTC | ↗ |
| LlamaParse Agentic PlusThe same page at the platform's most accurate tier | structure from a page $0.0375 per page | confirmed 22 Nov 14:08 UTC | ↗ |
| LlamaParse AgenticA page parsed by an agent, returned as markdown with its tables and charts | structure from a page $0.015 per page | confirmed 22 Nov 14:08 UTC | ↗ |
| LlamaParse Cost-effectiveA page parsed with a language model, returned as markdown | structure from a page $0.0045 per page | confirmed 22 Nov 14:08 UTC | ↗ |
Every figure is a row the boards on /markets carry, at the precision LlamaIndex published it, and each product opens onto its whole recorded history with the document behind every stretch. A product belongs to LlamaIndex because the register says LlamaIndex sells it, never because a board spells the name the same way. Read from the record, so each row carries the read that last confirmed it.
The pages of LlamaIndex the collector reads
| Page | Read | What the register says |
|---|---|---|
| developers.llamaindex.ai/llamaparse/general/pricing/llamaparse-pricing-md | every hour | The docs' markdown mirror, which carries both halves of a credit price: the credit's own rate and the credits a page of each tier costs. Neither figure is a price on its own. |
A page is read whole, on its own schedule, and every read is kept with the sha256 of the bytes that came back, so any figure above can be taken back to the document it was read from. A retired page keeps its row and its history and is no longer fetched. Whether each read parsed is on the collector page, which reads it live from the record.
