xai/grok-4.7
xAI's Grok 4.7, a frontier reasoning model for coding, agentic tasks, and knowledge work. Accepts text and image inputs, and supports function calling, structured outputs, and configurable reasoning effort (low, medium, high, xhigh).
$2.00 in · $6.00 out / 1M500,000 ctx
xai/grok-4.6
xAI's Grok 4.6, a flagship reasoning model for coding, agentic tasks, and visual work. Accepts text and image inputs, and supports function calling and structured outputs.
$2.00 in · $6.00 out / 1M500,000 ctx
xai/grok-4.5
xAI's Grok 4.5, a frontier model built for coding, agentic tasks, and knowledge work. Accepts text and image inputs, and supports function calling, structured outputs, and configurable reasoning effort (low, medium, high).
$2.00 in · $6.00 out / 1M500,000 ctx
xai/grok-4.20-0309-non-reasoning
xAI's Grok 4.20 non-reasoning model. Skips the thinking trace for fast, single-pass responses while keeping the same training as the reasoning variant.
$2.00 in · $6.00 out / 1M2,000,000 ctx
xai/grok-4.20-0309-reasoning
xAI's Grok 4.20 reasoning model. Uses extended thinking to work through complex problems, returning a reasoning trace alongside the final answer.
$2.00 in · $6.00 out / 1M2,000,000 ctx
xai/grok-4.3
xAI's Grok 4.3 model with a 1M-token context window and strong agentic tool calling with minimal hallucinations. Accepts text and image inputs, and supports function calling, structured outputs, and configurable reasoning effort (none, low, medium, high).
$1.25 in · $2.50 out / 1M1,000,000 ctx