Starting at $0.20/M input tokensStarting at $0.50/M output tokens
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. Reasoning can be enabled using the reasoningenabled parameter in the API. Learn more in our docs
Prompts and completions on Grok 4 Fast Free may be used by xAI or OpenRouter to improve future models.
xAI: Grok 4 Fast – Uptime and Availability | OpenRouter