xAI Rate Limits by Tier
What are xAI's API rate limits?
xAI's entry tier (Default) allows an unpublished number of requests/min and an unpublished number of tokens/min for documented default/model family. Limits scale up through Default as cumulative spend and account age increase — see the full table below, verified 2026-08-14.
Limits by tier
| Tier | Qualification | Model class | RPM | TPM | RPD | Concurrent |
|---|---|---|---|---|---|---|
| Default | Account/project limit shown in the xAI console | documented default/model family | — | — | — | — |
— means not documented by xAI, never a guess.
What this means for your workload
Classification at volume: 116 calls/min and 60,320 tokens/min at the production profile.
This provider publishes no numeric cap for this workload; check the account console before launch.
Response headers
retry-after | Seconds to wait before retrying, when supplied with a 429 |
rate-limit response headers | Provider-specific remaining and reset counters when documented |
When you exceed the limit
xAI returns HTTP 429.
Use the limit shown for the selected model and project, then back off.
FAQ
What happens when I exceed xAI's rate limit?
xAI returns HTTP 429. Use the limit shown for the selected model and project, then back off.
How do I request a rate limit increase on xAI?
Request one from the account dashboard: https://console.x.ai
Batch 48 · xai rate-limit decision and evidence modules. Surface verification: 2026-08-14. These are dated, route-local fixtures, not live quota claims.
xAI spend-tier and model-limit resolver
Frozen xai evidence board: Tier 0–4 · enterprise · text · multi-agent · embedding · voice · image. Formula / decision rule: text limit applies only to exact model/modality; otherwise Unavailable
| Frozen fixture | Inputs and observation | Formula / boundary | State |
|---|---|---|---|
batch48-xai-m1-r1Tier 0–4 · enterprise | principal/account=joined; endpoint=joined; model/pool=joined; bucket/window=joined; observed=2026-08-14 The primary identity and product joins are present for this frozen fixture. | text limit applies only to exact model/modality; otherwise Unavailable A missing provider, product, account, endpoint, model, bucket, or time-window join fails closed; no value is copied across routes. | PASS WITH SCOPE — frozen observation only. |
batch48-xai-m1-r2text · multi-agent · embedding | request/response/error=joined; limit/remaining/reset=observed; retry identity=joined; region=joined The response evidence is usable only for the named bucket and time window; no neighboring provider is borrowed. | text limit applies only to exact model/modality; otherwise Unavailable A missing provider, product, account, endpoint, model, bucket, or time-window join fails closed; no value is copied across routes. | PASS WITH LIMIT — dated evidence only. |
batch48-xai-m1-r3voice · image | workload=joined; prompt/output reserve=explicit; shared pool=declared; unknown=Unavailable; owner=platform Admission or recovery is withheld where the account-specific value or side-effect identity is absent. | text limit applies only to exact model/modality; otherwise Unavailable A missing provider, product, account, endpoint, model, bucket, or time-window join fails closed; no value is copied across routes. | UNAVAILABLE — live owner evidence required. |
Provenance: Frozen Batch 48 xai fixture: module 1 observation and calculation. First-party evidence checked 2026-08-14; unresolved joins fail closed. Surface verification date: 2026-08-14. xAI API docs (first-party source)
Sub-minute burst-shaping simulator
Frozen xai evidence board: evenly spaced · full-minute burst · 10-worker · 100-worker fan-out · long prompts · long outputs. Formula / decision rule: admit schedule = both RPS headroom and TPM headroom at every second
| Frozen fixture | Inputs and observation | Formula / boundary | State |
|---|---|---|---|
batch48-xai-m2-r1evenly spaced · full-minute burst | principal/account=joined; endpoint=joined; model/pool=joined; bucket/window=joined; observed=2026-08-14 The primary identity and product joins are present for this frozen fixture. | admit schedule = both RPS headroom and TPM headroom at every second A missing provider, product, account, endpoint, model, bucket, or time-window join fails closed; no value is copied across routes. | PASS WITH SCOPE — frozen observation only. |
batch48-xai-m2-r210-worker · 100-worker fan-out | request/response/error=joined; limit/remaining/reset=observed; retry identity=joined; region=joined The response evidence is usable only for the named bucket and time window; no neighboring provider is borrowed. | admit schedule = both RPS headroom and TPM headroom at every second A missing provider, product, account, endpoint, model, bucket, or time-window join fails closed; no value is copied across routes. | PASS WITH LIMIT — dated evidence only. |
batch48-xai-m2-r3long prompts · long outputs | workload=joined; prompt/output reserve=explicit; shared pool=declared; unknown=Unavailable; owner=platform Admission or recovery is withheld where the account-specific value or side-effect identity is absent. | admit schedule = both RPS headroom and TPM headroom at every second A missing provider, product, account, endpoint, model, bucket, or time-window join fails closed; no value is copied across routes. | UNAVAILABLE — live owner evidence required. |
Provenance: Frozen Batch 48 xai fixture: module 2 observation and calculation. First-party evidence checked 2026-08-14; unresolved joins fail closed. Surface verification date: 2026-08-14. xAI API docs (first-party source)
xAI 429 replay-safety ledger
Frozen xai evidence board: simple chat · streamed reasoning · parallel tools · live-search · idempotent write · non-idempotent write. Formula / decision rule: replay = request/tool identity ∧ checkpoint ∧ effect key; missing side-effect identity blocks replay
| Frozen fixture | Inputs and observation | Formula / boundary | State |
|---|---|---|---|
batch48-xai-m3-r1simple chat · streamed reasoning | principal/account=joined; endpoint=joined; model/pool=joined; bucket/window=joined; observed=2026-08-14 The primary identity and product joins are present for this frozen fixture. | replay = request/tool identity ∧ checkpoint ∧ effect key; missing side-effect identity blocks replay A missing provider, product, account, endpoint, model, bucket, or time-window join fails closed; no value is copied across routes. | PASS WITH SCOPE — frozen observation only. |
batch48-xai-m3-r2parallel tools · live-search | request/response/error=joined; limit/remaining/reset=observed; retry identity=joined; region=joined The response evidence is usable only for the named bucket and time window; no neighboring provider is borrowed. | replay = request/tool identity ∧ checkpoint ∧ effect key; missing side-effect identity blocks replay A missing provider, product, account, endpoint, model, bucket, or time-window join fails closed; no value is copied across routes. | PASS WITH LIMIT — dated evidence only. |
batch48-xai-m3-r3idempotent write · non-idempotent write | workload=joined; prompt/output reserve=explicit; shared pool=declared; unknown=Unavailable; owner=platform Admission or recovery is withheld where the account-specific value or side-effect identity is absent. | replay = request/tool identity ∧ checkpoint ∧ effect key; missing side-effect identity blocks replay A missing provider, product, account, endpoint, model, bucket, or time-window join fails closed; no value is copied across routes. | UNAVAILABLE — live owner evidence required. |
Provenance: Frozen Batch 48 xai fixture: module 3 observation and calculation. First-party evidence checked 2026-08-14; unresolved joins fail closed. Surface verification date: 2026-08-14. xAI API docs (first-party source)