grok-4-fast-non-reasoning API pricing
Blended at 3:1 input to output: $1.56 per million tokens.
xAI charges $1.25 per million input tokens and $2.50 per million output tokens.
Against the models nearest in price
Blended at a 3:1 input to output ratio.
| Source | ||||||
|---|---|---|---|---|---|---|
| grok-4-fast-non-reasoning This model | xAI | $1.25 | $2.50 | 2,000,000 | $1.56 | ↗ |
| grok-4 | xAI | $1.25 | $2.50 | 256,000 | $1.56 | ↗ |
| grok-4.20 | OpenRouter | $1.25 | $2.50 | 1,000,000 | $1.56 | ↗ |
| grok-4.20-multi-agent | OpenRouter | $1.25 | $2.50 | 1,000,000 | $1.56 | ↗ |
| grok-4.3 | OpenRouter | $1.25 | $2.50 | 1,000,000 | $1.56 | ↗ |
| grok-3 | xAI | $1.25 | $2.50 | 131,072 | $1.56 | ↗ |
| grok-3-beta | xAI | $1.25 | $2.50 | 131,072 | $1.56 | ↗ |
| grok-3-fast-beta | xAI | $1.25 | $2.50 | 131,072 | $1.56 | ↗ |
| grok-3-fast-latest | xAI | $1.25 | $2.50 | 131,072 | $1.56 | ↗ |
Last checked . Methodology
Questions
How much does grok-4-fast-non-reasoning cost per million tokens?
$1.25 per million input tokens and $2.50 per million output tokens, with cached input at $0.200. At a 3:1 input to output mix that blends to $1.56. Checked 12 Sept 2026.
What would grok-4-fast-non-reasoning cost for a real workload?
A thousand requests a day at 2,000 input and 600 output tokens each comes to $120.00 a month.
What is the context window for grok-4-fast-non-reasoning?
2,000,000 tokens of input, with up to 2,000,000 tokens of output.
grok-4 · grok-4.20 · grok-4.20-multi-agent · grok-4.3 · grok-3 · All xAI models · Cost calculator