run-llama/llama_cloud_services
1
0
Fork 0
mirror of https://github.com/run-llama/llama_cloud_services.git synced 2026-08-26 16:56:36 -04:00
Code Issues 352 Packages Projects Releases 10 Wiki Activity

Inaccurate page count and credit usage in parse API response #549

New Issue
Open
opened 2026-02-16 00:18:13 -05:00 by yindo · 0 comments
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
I'm seeing wildly inaccurate page count and credit usage fields in the job result response metadata. For example, for a new parse job with a PDF that has exactly 15 pages, I get:

[GET https://api.cloud.llamaindex.ai/api/v1/parsing/job/{job_id}/result/text]
{ 
    'text': '...',
    'job_metadata':
    {
        'credits_used': 0,
        'job_credits_usage': 0,
        'job_pages': 11,
        'job_auto_mode_triggered_pages': 0,
        'job_is_cache_hit': False
    }
}

This is using parse_document_with_llm. Similar results are obtained with other PDFs (inaccurate page count, 0 credit usage despite cache miss). Incidentally, I'm also seeing much higher credit usage than expected for this parsing mode (unsure if these are related).

Files
N/A

Job ID
One example: 6382d2ba-8d2d-4089-91fb-a35bae5e17f8

Client:
Please remove untested options:

  • API
  • Frontend (cloud.llamaindex.ai)
  • Notebook

Additional context
These results were replicated across the API and frontend.

Originally created by @bmeisburger on GitHub (Oct 2, 2025). **Describe the bug** I'm seeing wildly inaccurate page count and credit usage fields in the job result response metadata. For example, for a new parse job with a PDF that has exactly 15 pages, I get: ``` [GET https://api.cloud.llamaindex.ai/api/v1/parsing/job/{job_id}/result/text] { 'text': '...', 'job_metadata': { 'credits_used': 0, 'job_credits_usage': 0, 'job_pages': 11, 'job_auto_mode_triggered_pages': 0, 'job_is_cache_hit': False } } ``` This is using `parse_document_with_llm`. Similar results are obtained with other PDFs (inaccurate page count, 0 credit usage despite cache miss). Incidentally, I'm also seeing much higher credit usage than expected for this parsing mode (unsure if these are related). **Files** N/A **Job ID** One example: `6382d2ba-8d2d-4089-91fb-a35bae5e17f8` **Client:** Please remove untested options: - API - Frontend (cloud.llamaindex.ai) - Notebook **Additional context** These results were replicated across the API and frontend.
yindo added the bug label 2026-02-16 00:18:13 -05:00
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#549
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?