xAI Grok
Try xAI Grok on us. Starter credit covers your first requests, then one key reaches all 9 xAI Grok models, with the privacy posture shown on every route.
xAI Grokgrok
These privacy labels describe xAI Grok, the upstream model provider. Confidential requires all three: verified provider compute, end-to-end encryption and explicit zero data retention. Account and billing metadata are outside the content-retention claim.
| Provider | xAI Grok |
|---|---|
| API operator country | US Legal home of the API operator, not an inference-location guarantee. |
| Headquarters | Not verified |
| Routing status | Active |
| Provider website | https://x.ai/ |
| Models | 9 public models |
| Credits routes | 9 |
| Zero data retention | not claimed |
| Verified confidential inference | Not verified |
| Policy note | xAI documents no training on API requests and 30-day default audit retention, with ZDR as an enterprise feature. Policy source |
Inference locations
Provider API declarations are also available on each model's endpoint API. Direct chat and Responses replies separate advertised availability from serving location in usage.inference_location; the actual serving region remains unknown when not reported.
usage.provider_usage.gateway_region identifies the TrustedRouter gateway, not the provider's inference location. A value such as europe-west4 does not mean the model ran in Europe. usage.inference_location.serving_region remains null when the provider has not reported it. Older gateways may return the gateway-only field as provider_usage.region.
Where the upstream GPUs execute the model, not the provider's headquarters, API ingress, or data storage. ZDR and confidential inference do not by themselves restrict geography.
- Declared countries or regions
- Not verified
No inference-location declaration has been verified for this provider. - Can locations change?
- Not verified. Do not assume that the serving location is fixed.
- Provider region pinning
- Not verified.
- Pinning through TrustedRouter
- No verified provider-specific location pin documented here.
- Infrastructure declaration
- Inference location not verified; no country-specific residency commitment.
- Evidence
- Not yet reviewed.
Provider selection alone is not a region pin. TrustedRouter's US provider filter selects company jurisdiction, not GPU location. A regional gateway hostname does not pin a downstream GPU. For a binding residency requirement, confirm the model, region, failover scope and enforced controls before sending sensitive data.
Measured performance
19 samplesContinuously sampled across xAI Grok's routed models: p50 TTFT, effective throughput, and success rate. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.
| p50 TTFT | 1586 ms |
|---|---|
| Effective throughput | 67 tok/s n=1 |
| Uptime | 100.00% |
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| x-ai/grok-4.5 | 1345 ms | — | 100.00% | — | 3 |
| x-ai/grok-4.3 | 1496 ms | — | 100.00% | — | 1 |
| x-ai/grok-4.6 | 1541 ms | — | 100.00% | — | 5 |
| x-ai/grok-build-0.1 | 1586 ms | — | 100.00% | 1 provider_error |
4 |
| x-ai/grok-4.7 | 1744 ms | 67 tok/s n=1 | 100.00% | — | 5 |
| x-ai/grok-4.20 | 2061 ms | — | 100.00% | 2 provider_error |
1 |
xAI Grok performance history · Full provider & model leaderboard.
Models served by xAI Grok.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Input | Cached input | Output |
|---|---|---|---|---|---|
x-ai/grok-4.20SpaceXAI: Grok 4.20 |
IQ 111#72 | 2,000,000 | $1.31875/1M | $0.211/1M to $0.422/1M | $2.6375/1M |
x-ai/grok-4.20-reasoninggrok-4.20-0309-reasoning |
— | 0 | $1.31875/1M | $0.211/1M to $0.422/1M | $2.6375/1M |
x-ai/grok-4.3SpaceXAI: Grok 4.3 |
IQ 112#67 | 1,000,000 | $1.31875/1M | $0.211/1M to $0.422/1M | $2.6375/1M |
x-ai/grok-4.5SpaceXAI: Grok 4.5 |
IQ 122#36 | 500,000 | $2.11/1M | $0.3165/1M to $0.633/1M | $6.33/1M |
x-ai/grok-4.6SpaceXAI: Grok 4.6 |
IQ 126#22 | 500,000 | $2.11/1M | $0.5275/1M to $1.055/1M | $6.33/1M |
x-ai/grok-4.7SpaceXAI: Grok 4.7 |
IQ 127#19 | 500,000 | $2.11/1M | $0.5275/1M to $1.055/1M | $6.33/1M |
x-ai/grok-build-0.1SpaceXAI: Grok Build 0.1 |
— | 256,000 | $1.055/1M | $0.211/1M to $0.422/1M | $2.11/1M |
x-ai/grok-imagine-videoxAI Grok Imagine Video |
— | 10,000 | selected route | Not published | selected route |
x-ai/grok-voice-tts-1.0xAI: Grok Voice TTS 1.0 |
— | 60000 characters | $15.825/M characters | Not applicable | Included |
Questions
Does xAI Grok have zero data retention?
TrustedRouter does not currently mark xAI Grok as provider-level zero data retention. Use trustedrouter/zdr or provider.min_privacy=zdr to select a different eligible route, and review the linked policy source for changes.
Is xAI Grok end-to-end encrypted?
TrustedRouter does not currently mark xAI Grok as end-to-end encrypted at the provider boundary. The TrustedRouter gateway is still attested, but the selected provider normally receives the request in order to run the model. Use trustedrouter/e2e for the stronger route requirement.
Which xAI Grok models are available through TrustedRouter?
This page currently lists 9 public xAI Grok models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.