xAI: Grok 4 Fast

xAIID: x-ai/grok-4-fast

Grok 4 Fast is xAI's latest multimodal model with SOTA cost-efficiency and a 2M token context window. It comes in two flavors: non-reasoning and reasoning. Read more about the model on xAI's [news post](http://x.ai/news/grok-4-fast). Reasoning can be enabled/disabled using the `reasoning` `enabled` parameter in the API. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#controlling-reasoning-tokens)

Pricing per 1M Tokens

Input (Prompt)$0.20
Output (Completion)$0.50
Cache Read$0.05
Cache WriteFree
ImageN/A

Specifications

Context Length2M
Max Output Tokens30K
Input ModalitiesText + Image
Output ModalitiesText
TokenizerGrok
Instruct TypeN/A
Top Provider Context2M
Top Provider Max Output30K
ModeratedNo

Compare this model

See how xAI: Grok 4 Fast stacks up against other models.

vs xAI: Grok 4.20 Multi-Agent Betavs xAI: Grok 4.20 Betavs xAI: Grok 4.1 Fastvs xAI: Grok Code Fast 1vs xAI: Grok 4

More from xAI

xAI: Grok 4.20 Multi-Agent Beta
Input$2.00
Context2M
xAI: Grok 4.20 Beta
Input$2.00
Context2M
xAI: Grok 4.1 Fast
Input$0.20
Context2M
xAI: Grok Code Fast 1
Input$0.20
Context256K
xAI: Grok 4
Input$3.00
Context256K

Last updated: March 23, 2026

First tracked: March 23, 2026