← Model list

Grok 4.20 (Reasoning)

xai·xai/grok-4.20-0309-reasoning·BETA·Closed·grok series

Reasoning Grok for document-heavy analysis and long-horizon tool use

At a glance
Official price$1.25 / $2.50 per 1M
Cache read $0.20 · xAI
Lowest paid$1.25 / $2.50
Impossibl Gateway · 3.2× spread
Context1,000,000
⚠ Providers report 262,000–2,000,000; the table below is authoritative
Output limit30,000
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
TextImagePDF
Knowledge cutoff2025-09
Released / updated2026-03-09 / 2026-03-09

Quality & performance

Artificial Analysis doesn't cover this model (267 of 2059 have data). Quality data comes from independent evals covering widely used models.

Available at 8 providers8 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
ImpossiblGateway$1.25$2.50$0.201,000,00030,000
xAIOfficialFirst-party$1.25
tiered >200K: $2.50
$2.50$0.201,000,00030,000
Vercel AI Gateway
spacexai/grok-4.20-reasoning
Cloud$1.25$2.50$0.202,000,0002,000,000
Eden AIGateway$1.25
tiered >200K: $2.50
$2.50$0.201,000,00030,000
DevPass (LLM Gateway)
grok-4-20-reasoning
Gateway$1.25
tiered >200K: $2.50
$2.50$0.202,000,00030,000
Azure
grok-4-20-reasoning
First-party$2.00$6.00262,0008,192beta
DevPass (LLM Gateway)
grok-4-20-beta-0309-reasoning
Gateway$2.00
tiered >200K: $2.50
$6.00$0.202,000,00030,000
Ofox
x-ai/grok-4.20
Gateway$4.00$12.00$0.402,000,000128,000

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

1Impossibl$249.00
2xAI · Official$249.00
3Vercel AI Gateway$249.00
4Eden AI$249.00
5DevPass (LLM Gateway)$249.00
6DevPass (LLM Gateway)$484.00
Switch to Impossibl to save $0.00/mo (0%). The gap is small, so staying on the official channel is fine.
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 = high

6 / 8 providers expose no reasoning control (reasoning_options: []).

Related models

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$2.50$02026-08-052026-08-132026-08-05 · Input list $1.252026-08-06 · Input list $1.252026-08-07 · Input list $1.252026-08-08 · Input list $1.252026-08-09 · Input list $1.252026-08-10 · Input list $1.252026-08-11 · Input list $1.252026-08-12 · Input list $1.252026-08-13 · Input list $1.252026-08-05 · Output list $2.502026-08-06 · Output list $2.502026-08-07 · Output list $2.502026-08-08 · Output list $2.502026-08-09 · Output list $2.502026-08-10 · Output list $2.502026-08-11 · Output list $2.502026-08-12 · Output list $2.502026-08-13 · Output list $2.502026-08-05 · Min blended $1.562026-08-06 · Min blended $1.562026-08-07 · Min blended $1.562026-08-08 · Min blended $1.562026-08-09 · Min blended $1.562026-08-10 · Min blended $1.562026-08-11 · Min blended $1.562026-08-12 · Min blended $1.562026-08-13 · Min blended $1.56