Grok 4.20
Grok 4.20 is a reasoning model developed by SpaceXAI designed for complex tasks and agentic workflows. It supports text, image, and file inputs while offering high-capacity context and specialized tool-calling capabilities.
Grok 4.20 specs and pricing
- Provider: SpaceXAI
- Released: March 31, 2026
- Context window: 2M tokens
- Max output: 1.8M tokens
- Input: text, images, files
- Output: text
- Price: $1.25 input / $2.50 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Grok 4.20 is good at
- Processing large documents and image-based data
- Complex reasoning tasks requiring strict prompt adherence
- Automated agentic workflows that utilize external tools
To-dos to try with Grok 4.20
- Upload a 500-page technical manual and extract all safety protocols into a structured table.
- Analyze a set of project images to identify discrepancies against the provided design file.
- Use tool calling to search live data sources and summarize current industry trends based on your specific criteria.
FAQ
- Who developed Grok 4.20? Grok 4.20 is developed by SpaceXAI.
- Can this model process visual information? Yes, the model supports both text and image inputs.
- How much does Grok 4.20 cost? Grok 4.20 costs $1.25 per million input tokens and $2.50 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 3.85 credits ($1 = 100 credits).
- What is the context window of Grok 4.20? Grok 4.20 can read up to 2M tokens at once and write up to 1.8M tokens in one reply.
- Can I use Grok 4.20 without coding? Yes. In todo.is you pick Grok 4.20 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.