Grok 4.7 from SpaceXAI is now available on AI Gateway as spacexai/grok-4.7. Requests using this model ID are automatically 40% off through September 27.
Grok 4.7 is designed for complex, long-running coding, document, and presentation tasks. It has a 500K-token context window and supports low, medium, high, and xhigh reasoning levels, giving you control over response speed and reasoning depth.
To use Grok 4.7:
import { streamText } from 'ai';
const result = streamText({ model: 'spacexai/grok-4.7', reasoning: 'xhigh', prompt: 'Investigate the failing tests, identify the root cause, and propose a fix.',});To create an agent with eve, pass the same model ID and choose a reasoning level:
npx eve@latest init grok-agent \ --model spacexai/grok-4.7 \ --reasoning xhighCreate an eve agent with Grok 4.7 and xhigh reasoning.
Try Grok 4.7 in the model playground, see the coding agents guide for agent-specific setup instructions, or check out more discounted models on AI Gateway.