Grok 4.3

Grok 4.3 is xAI’s previous Grok 4-line API model. It remains available, with text and image input, text output, a 1M token context window, and official xAI token pricing. xAI’s current flagship recommendation is Grok 4.6.

What this model is

xAI lists the exact model name as grok-4.3, with aliases grok-4.3-latest. The model page describes Grok 4.3 as a fast, reliable model with strong tool calling and instruction following.

The official page lists a 1,000,000-token context window, function calling, structured outputs, and configurable reasoning levels of none, low, medium, and high. Batch API is listed as supported.

Pricing notes

xAI’s official Grok 4.3 model page lists API pricing at $1.25 per 1M input tokens, $0.20 per 1M cached input tokens, and $2.50 per 1M output tokens.

The calculator on this page uses the base uncached input and output rates: $1.25 input and $2.50 output per 1M tokens. xAI also notes that higher context pricing applies for requests exceeding 200K tokens. The checked Grok 4.3 page does not show the exact higher-context dollar amounts in the fetched summary, so those long-context rates are not stored as calculator fields.

Benchmarks and specs

xAI’s model page lists Grok 4.3 with text and image input, text output, a 1,000,000 token context window, function calling, structured outputs, and configurable reasoning levels of none, low, medium, and high.

This page does not show a parameter count or public benchmark score. Those numbers should only be shown when exact public sources are matched to grok-4.3 specifically.

Best fit

Grok 4.3 is best for existing integrations pinned to this snapshot, or for comparisons that need the 1M-context Grok 4.3 route rather than Grok 4.6’s 500k window.

For new general xAI work, xAI currently points to Grok 4.6.

Sources

• xAI Grok 4.3 model page
• xAI models overview