Pricing / xAI (Grok)

xAI (Grok) API pricing

39 model entries. xAI entries in the bundled pricing snapshot. Source rate fields are shown as encoded in the snapshot dated 2026-03-25; model modality is not encoded.

Lowest encoded input rate

$0.2/1M

grok-4-1-fast-reasoning

Highest encoded input rate

$5/1M

grok-vision-beta

Models with cache pricing

31 of 39

Interpret the /1M columns as token rates only for models independently verified as token-billed. Non-text billing units are not represented in this snapshot schema.

ModelInput $/1MOutput $/1MCache $/1M
grok-4-1-fast-reasoning$0.2$0.5$0.05
grok-4-1-fast-non-reasoning$0.2$0.5$0.05
grok-4-fast-non-reasoning$0.2$0.5$0.05
grok-4-fast-reasoning$0.2$0.5$0.05
grok-code-fast-1$0.2$1.5$0.02
grok-4-1-fast$0.2$0.5$0.05
grok-4-1-fast-reasoning-latest$0.2$0.5$0.05
grok-4-1-fast-non-reasoning-latest$0.2$0.5$0.05
grok-code-fast$0.2$1.5$0.02
grok-code-fast-1-0825$0.2$1.5$0.02
grok-3-mini$0.3$0.5$0.075
grok-3-mini-beta$0.3$0.5$0.075
grok-3-mini-latest$0.3$0.5$0.075
grok-3-mini-fast$0.6$4$0.15
grok-3-mini-fast-beta$0.6$4$0.15
grok-3-mini-fast-latest$0.6$4$0.15
grok-4.20-0309-reasoning$2$6$0.2
grok-4.20-0309-non-reasoning$2$6$0.2
grok-4.20-multi-agent-0309$2$6$0.2
grok-4$2$6$0.2
grok-2$2$10-
grok-2-1212$2$10-
grok-2-vision-1212$2$10-
grok-2-latest$2$10-
grok-2-vision$2$10-
grok-2-vision-latest$2$10-
grok-4-latest$2$6$0.2
grok-4.20-multi-agent-beta-0309$2$6$0.2
grok-4.20-beta-0309-reasoning$2$6$0.2
grok-4.20-beta-0309-non-reasoning$2$6$0.2
grok-3$3$15$0.75
grok-4-0709$3$15$0.75
grok-3-beta$3$15$0.75
grok-3-latest$3$15$0.75
grok-3-fast$5$25$1.25
grok-3-fast-beta$5$25$1.25
grok-3-fast-latest$5$25$1.25
grok-beta$5$15-
grok-vision-beta$5$15-

Use the xAI (Grok) snapshot as a reference, then measure the request

Local tracking can estimate supported responses from provider usage fields. The authenticated gateway path adds request identity, persisted cost evidence, session attribution, and pre-dispatch budget checks.