X Ai
xAI: 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)
| Specifications | |
|---|---|
| Provider | X Ai |
| Input pricing | $0.20/M tokens |
| Output pricing | $0.50/M tokens |
| Context length | 2.0M tokens |
| Max output | 30K tokens |
| Input modalities | textimagefile |
| Output modalities | text |
| Tokenizer | Grok |
| Knowledge cutoff | 2025-09-30 |
| Content moderated | No |
Supported Parameters
include_reasoninglogprobsmax_tokensreasoningresponse_formatseedstructured_outputstemperaturetool_choicetoolstop_logprobstop_p