run-llama/llama_cloud_services
1
0
Fork 0
mirror of https://github.com/run-llama/llama_cloud_services.git synced 2026-07-16 05:29:59 -04:00
Code Issues 352 Packages Projects Releases 10 Wiki Activity

"Parse document with LLM" listed cost is inconsistent #548

New Issue
Open
opened 2026-02-16 00:18:13 -05:00 by yindo · 1 comment
yindo commented 2026-02-16 00:18:13 -05:00
Owner
Copy Link
Copy Source

Originally created by @bmeisburger on GitHub (Oct 2, 2025).

Describe the bug
After testing several parsing models in the web UI sandbox, "Parse document with LLM" seemed to give me the best performance. The web UI advertises the cost as 3 credits/page. After running subsequently evals across several hundred pages, I was extremely confused why my credit usage was 10x higher than anticipated.

As it turns out, the "general" docs (https://developers.llamaindex.ai/python/cloud/general/pricing/) includes a pricing page (notably absent in the parsing docs) that lists "Parse document with LLM" as 30(!) credits/page. This is exacerbated by #938, which means that credit usage is/was not accurately reported in the response metadata, either.

Frustrating to have burnt through $50 of credits, and still need to spend hours repeating the evals with an entirely different model.

Originally created by @bmeisburger on GitHub (Oct 2, 2025). **Describe the bug** After testing several parsing models in the web UI sandbox, "Parse document with LLM" seemed to give me the best performance. The web UI advertises the cost as 3 credits/page. After running subsequently evals across several hundred pages, I was extremely confused why my credit usage was 10x higher than anticipated. As it turns out, the "general" docs (https://developers.llamaindex.ai/python/cloud/general/pricing/) includes a pricing page (notably absent in the parsing docs) that lists "Parse document with LLM" as 30(!) credits/page. This is exacerbated by [#938](https://github.com/run-llama/llama_cloud_services/issues/938), which means that credit usage is/was not accurately reported in the response metadata, either. Frustrating to have burnt through $50 of credits, and still need to spend hours repeating the evals with an entirely different model.
yindo added the bug label 2026-02-16 00:18:13 -05:00
yindo commented 2026-02-16 00:18:14 -05:00
Author
Owner
Copy Link
Copy Source

@Disiok commented on GitHub (Oct 2, 2025):

Hey @bmeisburger , apologies for the confusion, totally on us and we need to do better.

We will reach out to grant you additional credits to compensate for the effort/

@Disiok commented on GitHub (Oct 2, 2025): Hey @bmeisburger , apologies for the confusion, totally on us and we need to do better. We will reach out to grant you additional credits to compensate for the effort/
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
LlamaCloud
LlamaExtract
LlamaParse
bug
client
complex layout
documentation
duplicate
enhancement
figure
font
header footer
help wanted
ocr
parser
pdf_debug
pdf_debug
pull-request
Mirrored from GitHub Pull Request
 python-lib
question
server_issue
server_issue
ui
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: run-llama/llama_cloud_services#548
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?