LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← 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

Specs & pricing

Input / output per 1M tokens
Official price·xAI
$1.25 / $2.50
Blended $1.56 · Cache read $0.20
Lowest paid·xAIFirst-party
$1.25 / $2.50
Blended $1.56 · 3.2× spread
Context
1,000,000
Output limit
30,000
Knowledge cutoff
2025-09
Released / updated
2026-03-09 / 2026-03-09
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImagePDF

Grok 4.20 (Reasoning) by xai is offered by 20 providers on this page. Its official list price is $1.25 per 1M input tokens and $2.50 per 1M output tokens. No paid channel is priced below the official list price. Prices vary about 3.2× across the providers that host it.

The context window is 1,000,000 tokens at the reference host, but hosts report different limits, from 262,000 to 2,000,000, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, and PDF. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2025-09.

Available at 20 providers20 with public prices

  • ProviderInput / Output
  • xAIOfficialFirst-party
    $1.25 / $2.50
    tiered >200K: $2.50
    Cache read $0.20Context 1,000,000Output limit 30,000
  • LLM GatewayGateway
    vertex-openai/grok-4-20-reasoning
    $1.25 / $2.50
    tiered >200K: $2.50
    Cache read $0.20Context 2,000,000 ⚠Output limit 30,000
  • DevPass (LLM Gateway)Gateway
    grok-4-20-reasoning
    $1.25 / $2.50
    tiered >200K: $2.50
    Cache read $0.20Context 2,000,000 ⚠Output limit 30,000
  • VertexCloud
    xai/grok-4.20-reasoning
    $1.25 / $2.50
    tiered >200K: $2.50
    Cache read $0.20Context 2,000,000 ⚠Output limit 30,000
  • Merge GatewayGateway
    $1.25 / $2.50
    tiered >200K: $2.50
    Cache read $0.20Context 1,000,000Output limit 1,000,000
  • Eden AIGateway
    $1.25 / $2.50
    tiered >200K: $2.50
    Cache read $0.20Context 1,000,000Output limit 30,000
  • Kilo GatewayGateway
    x-ai/grok-4.20
    $1.25 / $2.50
    Cache read $0.20Context 2,000,000 ⚠Output limit 1,800,000
  • OCI Generative AICloud
    xai.grok-4.20-reasoning
    $1.25 / $2.50
    tiered >200K: $2.50
    Cache read $0.20Context 1,000,000Output limit 30,000
  • Vercel AI GatewayCloud
    spacexai/grok-4.20-reasoning
    $1.25 / $2.50
    tiered >200K: $2.50
    Cache read $0.20Context 2,000,000 ⚠Output limit 2,000,000
  • ImpossiblGateway
    $1.25 / $2.50
    tiered >200K: $2.50
    Cache read $0.20Context 1,000,000Output limit 30,000
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
xAIOfficialFirst-party$1.25
tiered >200K: $2.50
$2.50$0.20—1,000,00030,000
LLM Gateway
vertex-openai/grok-4-20-reasoning
Gateway$1.25
tiered >200K: $2.50
$2.50$0.20—2,000,000 ⚠30,000
DevPass (LLM Gateway)
grok-4-20-reasoning
Gateway$1.25
tiered >200K: $2.50
$2.50$0.20—2,000,000 ⚠30,000
Vertex
xai/grok-4.20-reasoning
Cloud$1.25
tiered >200K: $2.50
$2.50$0.20—2,000,000 ⚠30,000
Merge GatewayGateway$1.25
tiered >200K: $2.50
$2.50$0.20—1,000,0001,000,000
Eden AIGateway$1.25
tiered >200K: $2.50
$2.50$0.20—1,000,00030,000
Kilo Gateway
x-ai/grok-4.20
Gateway$1.25$2.50$0.20—2,000,000 ⚠1,800,000
OCI Generative AI
xai.grok-4.20-reasoning
Cloud$1.25
tiered >200K: $2.50
$2.50$0.20—1,000,00030,000
Vercel AI Gateway
spacexai/grok-4.20-reasoning
Cloud$1.25
tiered >200K: $2.50
$2.50$0.20—2,000,000 ⚠2,000,000
ImpossiblGateway$1.25
tiered >200K: $2.50
$2.50$0.20—1,000,00030,000

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.

Reasoning control

effort = loweffort = mediumeffort = higheffort = none

11 / 20 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1xAI · Official$249.00
2LLM Gateway$249.00
3DevPass (LLM Gateway)$249.00
4Vertex$249.00
5Merge Gateway$249.00
6Eden AI$249.00
The cheapest paid channel is official.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$2.50$02026-08-052026-08-13
2026-08-13Input list $1.25Output list $2.50Min blended $1.56

Related models

Grok Imagine Video 1.5 Litesame series—Grok 4.7same series$2.00 / $6.00Grok Voice Transcribe 2.0same series—GLM-5.3-Flashcheaper alternative$0.15 / $0.50DeepSeek V4.1 Flash 1017cheaper alternative$0.15 / $0.60GPT-5.6 Lunacheaper alternative$0.20 / $1.20MiniMax-M3cheaper alternative$0.30 / $1.20Grok 4.20 (Non-Reasoning)same lab$1.25 / $2.50Grok 4.20 Multi-Agentsame lab$1.25 / $2.50
Data partly from models.dev (MIT) · xAI official docs ↗