specification: API Commons Rate Limits
specificationVersion: '0.1'
generated: '2026-07-19'
method: searched
source: https://docs.flex.ai/inference-api/reference/billing
provider: FlexAI
providerId: flexai
created: '2026-07-19'
modified: '2026-07-19'
tags:
  - Rate Limiting
  - Inference
description: >-
  FlexAI Token Factory enforces per-API-key request rate limits, tiered by
  account status (free vs. paid), plus a prepaid account budget. Exceeding the
  rate limit returns 429 with a Retry-After header; exhausting the account
  budget returns 402 Payment Required.
headers:
  limit: x-ratelimit-limit-requests
  remaining: x-ratelimit-remaining-requests
  reset: x-ratelimit-reset-requests
  retryAfter: Retry-After
responseCodes:
  throttled: 429
  paymentRequired: 402
limits:
  - name: Free tier requests
    scope: api_key
    metric: requests_per_minute
    limit: 10
    timeFrame: minute
  - name: Paid tier requests
    scope: api_key
    metric: requests_per_minute
    limit: 100
    timeFrame: minute
  - name: Custom / Enterprise
    scope: api_key
    metric: requests_per_minute
    limit: -1
    timeFrame: minute
    note: Higher limits available on request via dashboard or support@flex.ai.
budget:
  free_credit: "$10 free credit on new accounts"
  exhausted_response: 402 Payment Required
  minimum_top_up: "$5"
  auto_recharge: false