generated: '2026-08-26'
method: searched
source: https://docs.plamo.preferredai.jp/en/limit
name: Preferred Networks PLaMo API rate limits and quotas
description: >-
  Published quotas for the PLaMo API and PLaMo Chat, read from the provider's own "Limitations" page
  in the PLaMo reference documentation. PFN documents the numeric limits and which of them accept a
  quota-increase request, but does not document any rate-limit response headers or the HTTP status
  code returned on exhaustion — the docs say only that "API returns error".
limit_count: 7
rate_limits:
- name: Request rate (legacy models)
  scope: per-api-key
  window: 1 minute
  limit: 1000
  applies_to: plamo-2.2-prime and earlier models, and translation models
  quota_increase_requestable: false
  on_exhaustion: API returns an error (status code not documented)
- name: Request rate (current models)
  scope: per-api-key
  window: 1 minute
  limit: 100
  applies_to: plamo-3.0-prime family models
  quota_increase_requestable: false
  on_exhaustion: API returns an error (status code not documented)
- name: Spend quota
  scope: per-tenant
  window: 1 month
  limit: 1000000
  unit: JPY
  applies_to: All API usage aggregated across the tenant's projects
  quota_increase_requestable: true
  on_exhaustion: API requests are blocked once the quota is reached
- name: API keys
  scope: per-tenant
  limit: 10
  resource: api_key
  quota_increase_requestable: true
  on_exhaustion: Creating more than the limit returns an error
- name: Users
  scope: per-tenant
  limit: 10
  resource: user
  quota_increase_requestable: true
  on_exhaustion: Inviting more than the limit returns an error
- name: Projects
  scope: per-tenant
  limit: 50
  resource: project
  quota_increase_requestable: true
  on_exhaustion: Creating more than the limit returns an error; archived projects count toward it
- name: PLaMo Chat request rate
  scope: per-user
  window: 1 minute
  limit: 10
  applies_to: PLaMo Chat demo web application (not the API)
  quota_increase_requestable: false
  on_exhaustion: Returns an error
response_headers:
  documented: false
  observed: []
  note: >-
    No X-RateLimit-*, RateLimit-* or Retry-After header is documented anywhere in the PLaMo
    reference, and the API cannot be exercised anonymously to observe them — an unauthenticated
    request to https://api.platform.preferredai.jp/v1/models returns HTTP 400
    {"message":"missing key in request header"} before any rate-limit accounting. An agent therefore
    has no published runtime signal for remaining quota; only the documented static numbers above.
exhaustion_status_code: not documented
quota_increase_process:
  method: Support form
  url: https://support.plamo.preferredai.jp/
  note: >-
    Limits marked quota_increase_requestable are raised via the PLaMo API Help Center contact form.
    Tenant-level billing limits and alerts are additionally self-service in the API console.
billing_controls:
  levels:
  - name: Tenant quota
    description: Hard tenant usage ceiling, initially set low to prevent unexpected charges; increases require a form submission.
  - name: Tenant billing limit
    description: Configurable monthly maximum charge, freely adjustable within the tenant quota; API use is restricted automatically on reach.
  - name: Project budget limit
    description: Per-project usage limits and alerts, with daily and monthly token/spend visibility.
  source: https://docs.plamo.preferredai.jp/en/console
evidence:
- url: https://docs.plamo.preferredai.jp/en/limit
  status: 200
- url: https://docs.plamo.preferredai.jp/en/console
  status: 200
- url: https://api.platform.preferredai.jp/v1/models
  status: 400
  note: Unauthenticated probe; no rate-limit headers present on the response.