LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Grok 4.1 Fast

xai·xai/grok-4.1-fast·GA·Closed·grok series
xAI's fast agentic tool-calling model with a 2M context window; non-reasoning variant for low-latency responses

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·Jiekou.AIGateway
$0.19 / $0.48
Blended $0.26 · 1.1× spread
Context
2,000,000
Output limit
30,000
Knowledge cutoff
2025-11
Released / updated
2025-11-19 / 2025-11-19
Capabilities
Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImage

Grok 4.1 Fast by xai is offered by 9 providers on this page. Public prices are shown for 6 of them. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is Jiekou.AI at $0.19 / $0.475 per 1M. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.

The context window is 2,000,000 tokens at the reference host, but hosts report different limits, from 128,000 to 2,000,000, so the usable window depends on the provider you pick. It supports tool use and structured output. Accepted input modalities are Text and Image. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2025-11.

Available at 9 providers6 with public prices

  • ProviderInput / Output
  • Jiekou.AIGateway
    grok-4-1-fast-non-reasoning
    $0.19 / $0.48
    Context 2,000,000Output limit 30,000
  • Perplexity AgentGateway
    xai/grok-4-1-fast-non-reasoning
    $0.20 / $0.50
    Cache read $0.05Context 2,000,000Output limit 30,000deprecated
  • FrogBotGateway
    grok-4-1-fast-non-reasoning
    $0.20 / $0.50
    Cache read $0.05Context 2,000,000Output limit 128,000
  • VertexCloud
    xai/grok-4.1-fast-non-reasoning
    $0.20 / $0.50
    Cache read $0.05Context 128,000 ⚠Output limit 30,000deprecated
  • OfoxGateway
    $0.20 / $0.50
    Cache read $0.05Context 2,000,000Output limit 30,000
  • HeliconeGateway
    grok-4-1-fast-non-reasoning
    $0.20 / $0.50
    Cache read $0.05Context 2,000,000Output limit 30,000
  • PoeGateway
    xai/grok-4.1-fast-non-reasoning
    — / —
    Context 2,000,000Output limit 30,000deprecated
  • QiniuGateway
    — / —
    Context 2,000,000Output limit 2,000,000deprecated
  • QiniuGateway
    x-ai/grok-4.1-fast-non-reasoning
    — / —
    Context 2,000,000Output limit 2,000,000deprecated
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Jiekou.AI
grok-4-1-fast-non-reasoning
Gateway$0.19$0.48——2,000,00030,000
Perplexity Agent
xai/grok-4-1-fast-non-reasoning
Gateway$0.20$0.50$0.05—2,000,00030,000deprecated
FrogBot
grok-4-1-fast-non-reasoning
Gateway$0.20$0.50$0.05—2,000,000128,000
Vertex
xai/grok-4.1-fast-non-reasoning
Cloud$0.20$0.50$0.05—128,000 ⚠30,000deprecated
OfoxGateway$0.20$0.50$0.05—2,000,00030,000
Helicone
grok-4-1-fast-non-reasoning
Gateway$0.20$0.50$0.05—2,000,00030,000
Poe
xai/grok-4.1-fast-non-reasoning
Gateway————2,000,00030,000deprecated
QiniuGateway————2,000,0002,000,000deprecated
Qiniu
x-ai/grok-4.1-fast-non-reasoning
Gateway————2,000,0002,000,000deprecated

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

Common scenarios
1Perplexity Agent$47.00
2FrogBot$47.00
3Vertex$47.00
4Ofox$47.00
5Helicone$47.00
6Jiekou.AI$61.75
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.28$02026-08-052026-10-22
2026-10-22Input list —Output list —Min blended $0.26

Related models

Grok Imagine Video 1.5 Litesame series—Grok 4.7same series$2.00 / $6.00Grok Voice Transcribe 2.0same series—X-Ai/Grok-4-Fast-Reasoningsame lab—Grok 4.1 Fast (Reasoning)same lab—
Data partly from models.dev (MIT)