tokenstat
tokenstat

xAI: Grok-4-Fast-Non-Reasoning

xai/grok-4-fast-non-reasoning · rates as of · Benchmarks · Plans · Calculator

Fast Grok model for responsive chat, reasoning, and tool-assisted work

Cheapest input
$0.18
$/MTok · models.dev
Cheapest output
$0.45
$/MTok
Context
2M
tokens
Offers
8
2 sources

Offers

Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.

SourceProviderInputOutputCache readContext
models.devcheapestgrok-4-fast-non-reasoningJiekou.AI$0.18$0.45$02M
models.devxai/grok-4-fast-non-reasoningPoe$0.2$0.5$0.052M
models.devgrok-4-fast-non-reasoning302.AI$0.2$0.5$02M
models.devgrok-4-fast-non-reasoningAbacus$0.2$0.5$02M
models.devgrok-4-fast-non-reasoningHelicone$0.2$0.5$0.052M
LiteLLMxai/grok-4-fast-non-reasoning$0.2$0.5$0.05
LiteLLMgrok-4-fast-non-reasoning$0.2$0.5$0.05
LiteLLMazure_ai/grok-4-fast-non-reasoning$0.2$0.5$0.02

Capabilities

  • Tool calling
  • Structured output
  • Attachments
  • In: text
  • In: image
  • In: audio
  • Out: text
Knowledge cutoff: 2025-06Released: 2025-09-23Family: grok

See what you actually spent

tokenstat prices your local sessions at list rates like these, with the cache split kept honest. Free, open source, runs on your machine.

$ curl -fsSL https://tokenstat.ai/install.sh | bash