grok-4.3 API pricing

xAI charges $1.25 per million input tokens and $2.5 per million output tokens for grok-4.3, and $0.2 per million cached input tokens. A typical request of 1,000 input and 500 output tokens costs $0.0025, or $0.002 through the batch API.

Prices updated October 28, 2026
Input / 1M tokens
$1.25
Output / 1M tokens
$2.5
Cached input / 1M tokens
$0.2
Typical request
$0.0025
Calculate the cost of your prompt →

grok-4.3 price per million tokens

Token typeStandardBatch API
Input$1.25$1
Cached input$0.2$0.16
Output$2.5$2

grok-4.3 supports a 1M-token context window, up to 1M output tokens, image input, tool calling and reasoning.

What grok-4.3 costs per request

Request1 request1,000 requests1M requests
Short chat message (300 in, 200 out)$0.000875$0.88$875.00
Typical request (1K in, 500 out)$0.0025$2.50$2,500.00
Long document summary (20K in, 1K out)$0.0275$27.50$27,500.00
Coding agent step (50K in, 2K out)$0.0675$67.50$67,500.00

At standard rates. A token is about 4 characters of English text, so 1,000 tokens is roughly 750 words. xAI counts tokens with its own tokenizer, so the same text can be a different number of tokens.

Models with a similar price

ModelProviderInput / 1MCached input / 1MOutput / 1MTypical request
grok-4.20xAI$1.25$0.2$2.5$0.0025
grok-4.20-0309-non-reasoningxAI$1.25$0.2$2.5$0.0025
grok-4.20-0309-reasoningxAI$1.25$0.2$2.5$0.0025
grok-4.20-non-reasoningxAI$1.25$0.2$2.5$0.0025
grok-4.20-reasoningxAI$1.25$0.2$2.5$0.0025
gemini-3.6-flashGoogle Gemini$0.75$0.075$3.75$0.00263
gemini-3.7-flashGoogle Gemini$0.75$0.075$3.75$0.00263
gemini-3.8-flashGoogle Gemini$0.75$0.075$3.75$0.00263

Other xAI models

Source: xAI pricing.