Grok 4.3
Grok 4.3 is a reasoning model developed by SpaceXAI designed for complex instruction-following and agentic workflows. It supports both text and image inputs and features a large context window of one million tokens.
Grok 4.3 specs and pricing
- Provider: SpaceXAI
- Released: April 30, 2026
- Context window: 1M tokens
- Max output: 900K tokens
- Input: text, images, files
- Output: text
- Price: $1.25 input / $2.50 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Grok 4.3 is good at
- Complex reasoning tasks
- Multi-step agentic workflows
- Analyzing documents and images
To-dos to try with Grok 4.3
- Analyze a set of technical diagrams and summarize the key design constraints.
- Process a lengthy project brief and break it down into a sequence of executable tasks.
- Compare the data points across multiple uploaded files to identify inconsistencies.
FAQ
- What types of input can Grok 4.3 process? The model accepts text, images, and files as input.
- What is the primary focus of this model? Grok 4.3 is built for reasoning, instruction-following, and applications that require high factual accuracy.
- How much does Grok 4.3 cost? Grok 4.3 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 4.3? Grok 4.3 can read up to 1M tokens at once and write up to 900K tokens in one reply.
- Can I use Grok 4.3 without coding? Yes. In todo.is you pick Grok 4.3 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.