TokenBingeby JoDevelop
All model prices
xAI

grok-4-5

Official price

Model overview

Two dollars per million input tokens and six per million output make grok-4-5 the only Grok priced above the rest of the line, and the surcharge does not buy context: the window stops at 500,000 tokens, half of what grok-4-3 and every 4.20 variant read for $1.25 in and $2.50 out. The premium is therefore 1.6x on input and 2.4x on output for a shorter window and the flagship label alone, since reasoning, tool calls and structured output are declared on all six entries. Its output-to-input ratio is the steepest in the range at three to one, so generation length drives the bill. Cached input at $0.30 is 15 percent of the miss rate, the deepest proportional cache discount xAI publishes.

Billing conditions: Standard short-context API price. At 200K input tokens or more, xAI applies its published long-context rates to all tokens in the request.

Context window
500,000 tokens
Knowledge cutoff
Price last verified
First observed

Descriptions, capabilities, and tariffs come from the linked source. First-party prices take priority; OpenRouter fallbacks are labelled.

Capabilities and formats

  • text
  • reasoning
  • tools
  • structured output

Performance references

No comparable benchmark data is currently available.

PRICE EVOLUTION

Price history

Original observation and every later change, including any change of price source.

  1. Original observed priceOfficial price unavailable
    Input: Cached input: Cache write 5m: Cache write 1h: Output:
  2. Price changeOfficial price
    Input: $2Cached input: $0.3Cache write 5m: Cache write 1h: Output: $6