xAI (Grok): Request limits switched from requests per minute to requests per second, derived as RPM / 60.
Old RPM and TPM caps per model
New RPS (= RPM / 60) and TPM caps per model
Why it matters: If you use xAI API (request rate limits), this changes how much you can send before requests are limited. The source does not state a separate effective date.
Alerts waitlist (not launched)
Joining sends nothing now; we keep your email only to tell you when alerts launch. Remove it any time: support@testedmcp.com. Stored by Netlify Forms. Privacy
| Product | xAI API (request rate limits) |
|---|---|
| Category | rate-limit |
| Announced / detected | between 2026-06-15 and 2026-07-06 Backfilled |
| Backfilled | Yes: added retroactively, detected between 2026-06-15 and 2026-07-06 |
| Quote verified against | https://web.archive.org/web/20260706202503/https://docs.x.ai/developers/rate-limits |
| Archive captures | https://web.archive.org/web/20260615234539/https://docs.x.ai/developers/rate-limits https://web.archive.org/web/20260706202503/https://docs.x.ai/developers/rate-limits |
| Effective | not stated in source |
| Before | RPM and TPM caps per model |
| After | RPS (= RPM / 60) and TPM caps per model |
| Official source | https://docs.x.ai/developers/rate-limits |
| Source quote | Your per-second limit is derived from your per-minute request budget (RPM / 60) |
| Archive | No post-change Wayback capture found |
| Snapshot hash | sha256:14d6624b6c52abdb737570ee827536a54376441c03e4ae1978215ad406020dc0 |
| Status | verified |
All xAI (Grok) changes · Dispute or correct this entry
Previous changes from xAI (Grok)
- between 2026-09-28 and 2026-10-13 Backfilled: Per-second request limit formula loosened from RPM / 60 to RPM / 48 with a minimum of 2.
- between 2026-09-10 and 2026-09-28 Backfilled: Voice models brought under the spend-based rate limit tiers.
- 2026-09-02: grok-imagine-image-quality retires 2026-11-02; requests will be served by grok-imagine-image-2.0 (quality=low) at a lower per-image price.
- 2026-06-15 Backfilled: A priority service tier became available on text inference endpoints; priority rates are billed only when priority is applied.
- between 2026-04-02 and 2026-04-13 Backfilled: Rate limit tiers consolidated from six to five (Tier 0-4) with new spend thresholds.
- between 2026-03-13 and 2026-03-23 Backfilled: Spend-based rate limit tiers introduced for text models, unlocking automatically by cumulative spend since Jan 1 2026.
How xAI (Grok) limits and pricing work · All changes, July 2026