Skip to content
llmprice

Grok 4.20 (Reasoning)

Updated Sep 11, 2026

grok2.0M context2.0M max outputreleased Mar 9, 2026ReasoningTool calling
Cheapest input
$1.25
Cheapest output
$2.5
Official (xAI)
$2.5
output per 1M tokens
Providers
10
offering this model
Spread
4.8×
max / min output

Offers

Metered per-token prices. Cheapest input and output are highlighted; marks a context-tier surcharge.

Provider1M input1M output1M cache read1M cache writeContext
Eden AICheapest$1.25Cheapest$2.5$0.21.0M
Vertex$1.25$2.5$0.22.0M
Impossibl$1.25$2.5$0.21.0M
DevPass (LLM Gateway)$1.25$2.5$0.22.0M
LLM Gateway$1.25$2.5$0.22.0M
Vercel AI Gateway$1.25$2.5$0.22.0M
Vercel AI Gateway$1.25$2.5$0.22.0M
xAI$1.25$2.5$0.21.0M
Azure$2$6262k
Cloudflare AI Gateway$2$6$0.22.0M
DevPass (LLM Gateway)$2$6$0.22.0M
LLM Gateway$2$6$0.22.0M
Ofox$4$12$0.42.0M

Other grok models