tokenstat
tokenstat

xAI: Grok 4.20 (Non-Reasoning)

xai/grok-4.20-non-reasoning · rates as of · Benchmarks · Plans · Calculator

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

Cheapest input
$1.25
$/MTok · models.dev
Cheapest output
$2.50
$/MTok
Context
2M
tokens
Offers
6
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-4.20-non-reasoningVercel AI Gateway$1.25$2.50$0.22M
models.devgrok-4-20-non-reasoningLLM Gateway$1.25$2.50$0.22M
models.devgrok-4-20-non-reasoningAzure$2$6$0262K
LiteLLMxai/grok-4.20-non-reasoning$2$6$0.2
LiteLLMgrok-4.20-non-reasoning$2$6$0.2
LiteLLMvertex_ai/xai/grok-4.20-non-reasoning$2$6$0.2

Capabilities

  • Tool calling
  • Structured output
  • Attachments
  • In: text
  • In: image
  • In: pdf
  • Out: text
Knowledge cutoff: 2025-09Released: 2026-04-08Family: 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