Coding-specialized model optimized for software engineering tasks with 256K context window. Priced at $1.00 input / $2.00 output per 1M tokens - 20% cheaper than Grok 4.3 for code-focused workflows. Ideal for agentic coding, refactors, and large codebase analysis.
- Coding-specialized model optimized for software engineering and agentic development workflows
- 256K context window enabling whole-repository analysis and large refactoring tasks
- 20% cheaper input/output than Grok 4.3 for cost-effective code generation at scale
- Function calling support for tool-driven coding agents and automated PR workflows
- Strong instruction following tuned for code generation, debugging, and review tasks
JSON Mode
Output responses in valid JSON format.
Model Information
Supported Formats
Grok 4.3xAI's latest flagship model released April 30, 2026, leading the industry in non-hallucination rate, agentic tool calling, and instruction following. Features 1M token context window with cached input at $0.20/M and supports function calling, structured outputs, image understanding, and live search.
Grok 4.20xAI's most advanced flagship model released March 2026 with 2M token context window. Features extended reasoning, multi-agent collaboration, and function calling capabilities. Supports cached input at $0.20/M tokens with 50% batch discount.
Grok 4.20 Non-ReasoningNon-reasoning variant of Grok 4.20 optimized for fast, direct responses without extended deliberation. Same 1M context window and image understanding as the reasoning variant, ideal for high-throughput workloads where step-by-step thinking is not required.