tokenstat
tokenstat

xAI: Grok 4

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

Grok model for agentic tool use, reasoning, coding, and live assistance

Cheapest input
$3
$/MTok · models.dev
Cheapest output
$15
$/MTok
Context
256K
tokens
Offers
14
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.devcheapestxai/grok-4Poe$3$15$0.75256K
models.devxai/grok-4Requesty$3$15$0.75256K
models.devgrok-4Helicone$3$15$0.75256K
models.devgrok-4LLM Gateway$3$15$0.75256K
models.devx-ai/grok-4FastRouter$3$15$0.75256K
models.devx-ai/grok-4ZenMux$3$15$0.75256K
LiteLLMx-ai/grok-4$3$15$0.3
LiteLLMgrok-4$3$15$0.3
LiteLLMazure_ai/grok-4$3$15$0.3
LiteLLMoci/xai.grok-4$3$15$0.3
LiteLLMopenrouter/x-ai/grok-4$3$15$0.3
LiteLLMvercel_ai_gateway/xai/grok-4$3$15$0.3
LiteLLMxai.grok-4$3$15$0.3
LiteLLMreplicate/xai/grok-4$7.20$36$0.72

Capabilities

  • Reasoning
  • Tool calling
  • Attachments
  • In: text
  • In: image
  • Out: text
Knowledge cutoff: 2025-01Released: 2025-07-10Family: 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