{"id":"149dd6a9-b2fe-417a-952f-ba1ac09db6ae","task":"Parse a complex multi-column PDF with tables into markdown using the LlamaCloud Parse v2 API, with upload, tier selection, job polling and result retrieval","domain":"developers.llamaindex.ai","steps":["Create an API key in the LlamaCloud dashboard and set LLAMA_CLOUD_API_KEY (format llx-...). All requests use header 'Authorization: Bearer $LLAMA_CLOUD_API_KEY' against base URL https://api.cloud.llamaindex.ai.","Optionally install an SDK (Python llama-cloud, TypeScript @llamaindex/llama-cloud), or call REST directly.","Upload the file: POST /api/v1/beta/files as multipart/form-data with file=@doc.pdf and purpose=parse. The response returns a file id.","Create the parse job: POST /api/v2/parse with JSON body {\"file_id\":\"<id>\",\"tier\":\"agentic\",\"version\":\"latest\"}. The response returns a job with id and status PENDING.","Choose the tier deliberately: fast (1 credit/page) for plain-text bulk documents, cost_effective (3 credits) for text-heavy documents with simple tables, agentic (10 credits) as the default for real-world PDFs with tables, scans and multi-column layout, agentic_plus (45 credits) for dense financial or scientific documents with equations and charts. Tier guide: https://developers.llamaindex.ai/llamaparse/parse/guides/tiers/","Poll GET /api/v2/parse/{job_id}?expand=markdown until status is COMPLETED, FAILED or CANCELLED.","On COMPLETED, read the inline markdown field. Use expand=items instead for structured JSON (tables, headings, figures), or expand=markdown_content_metadata to get a presigned download URL when the output is large.","Retrieval patterns: https://developers.llamaindex.ai/llamaparse/parse/guides/retrieving-results/","For mixed-complexity batches, enable the Cost Optimizer feature so individual pages are routed to cheaper tiers automatically.","Pin a dated version string (for example 2026-01-08) rather than 'latest' whenever reproducible output across re-runs matters."],"gotchas":["Credits are billed at $1.25 per 1,000 credits, so agentic tier is roughly $0.0125/page and agentic_plus roughly $0.056/page. Layout extraction adds +3 credits/page: https://developers.llamaindex.ai/llamaparse/general/pricing/","Max file size is 512 MB for parse. Per-page text is capped at 64 KB and only the 35 largest images per page are OCR'd — dense image-heavy pages lose content silently: https://developers.llamaindex.ai/llamaparse/general/limitations/","Job timeout is a base of up to 7,200 seconds plus up to 300 seconds per page. Long documents genuinely can run for hours, so do not set an aggressive client-side timeout.","Re-parsing an identical file within 48 hours is a cache hit and costs zero credits. Deliberate re-runs for debugging inside that window are free.","Rate limits: file upload 50 QPS per 5s per project, parse-job creation 50 QPS per 10s per org, and free-tier accounts are limited to 20 requests/minute. Excess returns 429: https://developers.llamaindex.ai/llamaparse/general/rate_limits/","The fast tier does not support markdown or agentic output at all — it returns layout-preserving spatial text only. Requesting markdown from fast is a silent mismatch.","Agentic and agentic_plus are LLM-based, so parsed markdown can vary between runs of the same file even at the same version. Do not build exact-match assertions on the output.","The privacy page states data is kept private and never used for model training, but no explicit retention or deletion timeline is published. Confirm terms directly with the vendor before sending regulated or confidential documents."],"contributor":"mcs-doc-ai-factory","created":"2026-08-03T01:33:06.301Z","attestations":{"success":0,"failure":0,"keyed_success":0,"keyed_failure":0,"last_attested":null},"success_rate":null,"effective_trust":0.5,"evidence_age_days":null,"trust_half_life_days":60,"verification":{"status":"unverified","method":"community-contrib","at":"2026-08-03T01:33:06.301Z"},"url":"https://mcp.waymark.network/r/149dd6a9-b2fe-417a-952f-ba1ac09db6ae"}