specification: API Commons Rate Limits
specificationVersion: '0.1'
schema: https://raw.githubusercontent.com/api-evangelist/interface-research/main/schema/api-commons.yml#/$defs/RateLimits
provider: Mendable
providerId: mendable
created: '2026-06-20'
modified: '2026-06-20'
reconciled: false
tags:
- AI
- Answers
- Enterprise Search
- RAG
- Support
- Rate Limiting
- Quotas
- Throttling
description: >-
  Mendable meters API usage primarily through a monthly message-credit
  allotment that varies by plan, where each chat answer consumes credits based
  on the model used. Beyond the message-credit quota, Mendable does not publish
  explicit per-second / per-minute request rate limits in its public API
  documentation; ingestion has documented payload limits (up to 500 raw
  documents and 2MB per ingestDocuments request). Specific request-rate values
  are not reconciled in this artifact.
notes: >-
  Verify the current message-credit allotment per plan and any per-endpoint
  request limits on reconciliation; quotas raise via Enterprise agreements.
sources:
- https://www.mendable.ai/pricing
- https://docs.mendable.ai/mendable-api/ingestion
- https://docs.mendable.ai/mendable-api/overview
responseCodes:
  throttled: 429
limits:
- name: Message Credits
  scope: account
  metric: messages
  limit: see plan (500/month on Free)
  notes: Each answer consumes credits by model; quota resets monthly and raises by plan.
- name: ingestDocuments Document Count
  scope: request
  metric: documents
  limit: 500
  notes: Maximum raw documents per ingestDocuments request.
- name: ingestDocuments Payload Size
  scope: request
  metric: bytes
  limit: 2097152
  notes: 2MB maximum payload per ingestDocuments request.
- name: API Request Rate
  scope: account
  metric: requests
  limit: see provider documentation
  notes: No explicit public per-minute request rate limit documented; not reconciled.
policies:
- name: Credit-Based Quota
  description: Usage is bounded by monthly message credits rather than per-second request rates; credits vary by model.
- name: Backoff Strategy
  description: Clients should implement exponential backoff with jitter and honor Retry-After on 429 responses.
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com