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: xAI
providerId: xai
created: '2026-05-08'
# Provenance stamped 2026-08-11: this artifact was written by the API Evangelist
# bulk sweep dated 2026-05-08, not harvested from the provider. See roadmap#35.
method: generated
modified: '2026-05-08'
reconciled: false
tags:
- AI
- LLM
- Foundation Models
- Grok
- Generative AI
- Rate Limiting
- Quotas
- Throttling
description: >-
  xAI enforces per-team rate limits on the synchronous API (requests per minute
  and tokens per minute) that vary by model and account tier. The Batch API does
  not count toward synchronous rate limits. Specific per-model limits are not
  reconciled in this artifact; consult the xAI Console for the active limits on
  your team.
notes: >-
  Pending reconciliation of per-model RPM/TPM/IPM/IPD limits per usage tier.
sources:
- https://docs.x.ai/docs/models
- https://console.x.ai/team/default/models
responseCodes:
  throttled: 429
limits:
- name: Requests Per Minute (RPM)
  scope: team
  metric: requests
  limit: see provider documentation
  notes: Per-model RPM, varies by tier and model. Pending reconciliation.
- name: Tokens Per Minute (TPM)
  scope: team
  metric: tokens
  limit: see provider documentation
  notes: Per-model TPM, varies by tier and model. Pending reconciliation.
- name: Batch API
  scope: team
  metric: requests
  limit: not counted against synchronous limits
  notes: Batch jobs run asynchronously and do not consume synchronous RPM/TPM.
policies:
- name: Backoff Strategy
  description: Clients should implement exponential backoff with jitter and honor any Retry-After header.
- name: Tiered Limits
  description: Higher usage tiers and enterprise agreements unlock higher per-minute limits.
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com