TokenBingeby JoDevelop
All model prices
xAI

grok-4-3

Official price

Model overview

Four of the six xAI entries share one rate card, and this is the one that is not a 4.20 variant: $1.25 per million input tokens, $0.20 cached, $2.50 output, over a 1,000,000-token window. Set against grok-4-5 that is 37.5 percent less on input, under half the output rate, and twice the context; set against the cheaper build model it is 25 percent more on both meters for roughly four times the window. Since grok-4-3 costs exactly what the reasoning, non-reasoning and multi-agent 4.20 builds cost, the comparison with them is behavioural rather than financial. Note the long-context rule: at 200,000 input tokens or more, xAI's published long-context rates apply to every token in the request, not just the excess.

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
1,000,000 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: $1.25Cached input: $0.2Cache write 5m: Cache write 1h: Output: $2.5