Skip to main content

​
Flow

  1. Upload a file with PUT /v1/blobs — same blob_id for all follow-on APIs.
  2. Parse with POST /v1/blobs/{blob_id}/parse — sync for small payloads; ?async=true for larger blobs or when you want QStash + optional HTTPS callback.
  3. Poll GET /v1/blobs/{blob_id}/parse/{parse_id} until complete or failed.
  4. Search semantically with GET /v1/blobs/search — natural-language query over embedded chunks.

​
Quotas

  • parse_ops — free-tier lifetime cap; starter/pro monthly caps (see GET /v1/billing and GET /v1/capabilities).
  • Parse rate limits — per-minute caps by tier (5 / 30 / 60 free / starter / pro).
  • Search — blob search shares web discovery + blob search quota (same counters as GET /v1/search).

​
Storage (billing)

KV memory (memory_storage_bytes) and blob chunk embeddings (blob_embed_storage_bytes) are reported separately; combined_memory_storage_bytes vs cap drives memory over_limit on GET /v1/billing.