tokenstat
tokenstat

xAI: Grok 4.1 Fast

xai/grok-4-1-fast · rates as of · Benchmarks · AI plans · Calculator

xAI's fast agentic tool-calling model with a 2M context window; non-reasoning variant for low-latency responses

Cheapest input
$0.18
$/MTok · models.dev
Cheapest output
$0.45
$/MTok
Context
2M
tokens
Sources
2
36 listings

Price changes

Cheapest list input/output only. Rates move rarely, so this is an event log. Down means cheaper. Showing the 8 latest changes.

Input $/MTok over sampled dates
Output $/MTok
  • ↓ lowerOutput $0.5 → $0.45
  • ↓ lowerInput $0.2 → $0.18

Sources

Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number.

SourceProviderInputOutputCache readContext
models.devcheapestgrok-4-1-fast-non-reasoningJiekou.AI$0.18$0.45$02M
models.devcheapestgrok-4-1-fast-reasoningJiekou.AI$0.18$0.45$02M
models.devx-ai/grok-4.1-fastOfox$0.2$0.5$0.052M
models.devxai/grok-4.1-fast-non-reasoningGoogle Vertex AI$0.2$0.5$0.05128K
models.devxai/grok-4-1-fast-non-reasoningPerplexity$0.2$0.5$0.052M
models.devgrok-4-1-fast-non-reasoningAbacus$0.2$0.5$02M
models.devgrok-4-1-fast-non-reasoningAzure$0.2$0.5$0.05128K
models.devgrok-4-1-fast-non-reasoningFrogBot$0.2$0.5$0.052M
models.devgrok-4-1-fast-non-reasoningHelicone$0.2$0.5$0.052M
models.devgrok-4-1-fast-non-reasoningDevPass (LLM Gateway)$0.2$0.5$0.052M
models.devgrok-4-1-fast-reasoning302.AI$0.2$0.5$02M
models.devgrok-4-1-fast-reasoningAzure$0.2$0.5$0.05128K
models.devgrok-4-1-fast-reasoningFrogBot$0.2$0.5$0.052M
models.devgrok-4-1-fast-reasoningHelicone$0.2$0.5$0.052M
models.devgrok-4-1-fast-reasoningDevPass (LLM Gateway)$0.2$0.5$0.052M
models.devxai/grok-4.1-fast-reasoningGoogle Vertex AI$0.2$0.5$0.05128K
models.devazure-ai-foundry/grok-4-1-fast-non-reasoningLLM Gateway$0.2$0.5$02M
models.devazure-ai-foundry/grok-4-1-fast-reasoningLLM Gateway$0.2$0.5$02M
models.devspacexai/grok-4.1-fast-non-reasoningVercel AI Gateway$0.2$0.5$0.051M
models.devspacexai/grok-4.1-fast-reasoningVercel AI Gateway$0.2$0.5$0.051M
LiteLLMxai/grok-4.1-fast-non-reasoningN/A$0.2$0.5$0.05N/A
LiteLLMgrok-4.1-fast-non-reasoningN/A$0.2$0.5$0.05N/A
LiteLLMgrok-4.1-fast-reasoningN/A$0.2$0.5$0.05N/A
LiteLLMxai/grok-4.1-fast-reasoningN/A$0.2$0.5$0.05N/A
LiteLLMazure_ai/grok-4-1-fast-non-reasoningN/A$0.2$0.5$0.02N/A
LiteLLMazure_ai/grok-4-1-fast-reasoningN/A$0.2$0.5$0.02N/A
LiteLLMvertex_ai/xai/grok-4.1-fast-non-reasoningN/A$0.2$0.5$0.05N/A
LiteLLMvertex_ai/xai/grok-4.1-fast-reasoningN/A$0.2$0.5$0.05N/A
LiteLLMxai/grok-4-1-fast-non-reasoningN/A$1.25$2.50$0.2N/A
LiteLLMgrok-4-1-fast-non-reasoningN/A$1.25$2.50$0.2N/A
LiteLLMgrok-4-1-fast-reasoningN/A$1.25$2.50$0.2N/A
LiteLLMxai/grok-4-1-fast-reasoningN/A$1.25$2.50$0.2N/A
LiteLLMgrok-4-1-fastN/A$1.25$2.50$0.2N/A
LiteLLMxai/grok-4-1-fastN/A$1.25$2.50$0.2N/A
LiteLLMoci/xai.grok-4.1-fastN/A$5$25$0.5N/A
LiteLLMxai.grok-4.1-fastN/A$5$25$0.5N/A

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments
  • In: text
  • In: image
  • In: pdf
  • Out: text
  • Out: image
Knowledge cutoff: 2025-07Released: 2025-11-20Family: grok

Run this model in a real workspace

Launch agents from the project they work in, use remote management to reach another machine, and see this model's sessions and token usage in your own history. Free to use, runs on your device.

CLI for macOS, Linux, and Windows

Data and list-price estimates may contain mistakes. Not investment advice.