← Model list

Grok 4.6

xai·xai/grok-4.6·GA·Closed·grok series·NEW

xAI's frontier model for long-running agents, coding, knowledge work, and visual projects

At a glance
Official price$2.00 / $6.00 per 1M
Cache read $0.50 · xAI
Lowest paid$1.50 / $4.50
Merge Gateway Gateway · 1.5× spread
Context500,000
Output limit500,000
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
Modalities
TextImagePDF
Knowledge cutoff2026-02-01
Released / updated2026-08-12 / 2026-08-12

Quality & performanceArtificial Analysis · Intelligence Index v4.1 · rep. tier high

Intelligence60.9
Value27
Coding76.8
Agentic58.7
Output speed56 tok/s
TTFT36.89 s
Cost per task$0.8367
Value formulaIQ 60.9 ÷ min blended $2.250 = 27

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 18 providers18 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Merge GatewayGateway$1.50$4.50$0.375500,000500,000
RequestyGateway$1.80
tiered >200K: $3.60
$5.40$0.45$1.80500,000500,000
NanoGPTGateway$2.00$6.00$0.50500,000500,000
OpenRouterGateway$2.00
tiered >200K: $4.00
$6.00$0.50500,000500,000
CrossModelGateway$2.00
tiered >200K: $4.00
$6.00$0.50$2.00500,000500,000
xAIOfficialFirst-party$2.00
tiered >200K: $4.00
$6.00$0.50500,000500,000
Perplexity AgentGateway$2.00
tiered >200K: $4.00
$6.00$0.50500,000500,000
OfoxGateway$2.00$6.00$0.50500,00065,536
OpenCode ZenGateway$2.00
tiered >200K: $4.00
$6.00$0.50500,000500,000
Vercel AI GatewayCloud$2.00$6.00$0.50500,000500,000

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

1Merge Gateway$390.00
2Requesty$468.00
3NanoGPT$520.00
4OpenRouter$520.00
5CrossModel$520.00
6xAI · Official$520.00
Switch to Merge Gateway to save $130.00/mo (25%)
Note: this is a gateway; verify availability and rate limits yourself.

Benchmark

No upstream benchmark data for this model. For quality, see the Artificial Analysis intelligence score above.

Reasoning control

effort = loweffort = mediumeffort = higheffort = xhigheffort = noneeffort = maxbudget_tokens

2 / 18 providers expose no reasoning control (reasoning_options: []).

Related models

Price historyone sample accumulated per data sync

Input list $2.00Output list $6.00Min blended $2.25

Price history accumulates from each data sync; currently only 1 sample(s) (2026-08-13). Each future sync adds a point, and once accumulated a line is drawn here.