Grok 4.7
Grok 4.7 is a flagship model developed by SpaceXAI designed for complex coding, agentic workflows, and knowledge-based tasks. It features a large 500,000-token context window and supports both text and image inputs to assist with long-running software engineering projects.
Grok 4.7 specs and pricing
- Provider: SpaceXAI
- Released: September 21, 2026
- Context window: 500K tokens
- Max output: 450K tokens
- Input: text, images, files
- Output: text
- Price: $2.00 input / $6.00 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Grok 4.7 is good at
- Complex software engineering and debugging
- Analyzing large documents and image-based data
- Autonomous agentic tasks requiring self-verification
To-dos to try with Grok 4.7
- Analyze this 300-page technical manual and identify all potential system integration errors.
- Review this codebase to suggest architectural improvements and verify the logic of the new modules.
- Process these architectural diagrams and text files to generate a comprehensive project summary report.
FAQ
- Who developed Grok 4.7? Grok 4.7 is developed by SpaceXAI as the successor to their previous model, Grok 4.6.
- What types of data can this model process? The model accepts text, images, and files as input and provides text-based outputs.
- How much does Grok 4.7 cost? Grok 4.7 costs $2.00 per million input tokens and $6.00 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 6.44 credits ($1 = 100 credits).
- What is the context window of Grok 4.7? Grok 4.7 can read up to 500K tokens at once and write up to 450K tokens in one reply.
- Can I use Grok 4.7 without coding? Yes. In todo.is you pick Grok 4.7 as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.