xAI: Grok 4.3

xAI: Grok 4.3

x-ai · Released Apr 30, 2026 Professional
Intelligence #13 / 610
82.0 Our Score
Speed #119 / 286
105.5 tokens / sec
Input #474 / 610
$1.25 per 1M tokens
Output #421 / 610
$2.50 per 1M tokens
Context #61 / 610
1M tokens

Analysis Summary

Grok 4.3 is a mid-generation release from xAI, sitting well below the Grok 4.5 flagship on both intelligence and coding benchmarks. It does bring a full 1M token context window, vision support, tool use, and function calling, which gives it broad capability breadth for its price tier.

For businesses, the large context window makes it useful for long-document analysis, contract review, or codebase-level tasks where fitting content into memory matters. However, its coding index and agentic scores are moderate, so it is not the right choice for complex autonomous agents or demanding software engineering tasks.

At $1.25 input and $2.50 output per million tokens it is competitively priced for its capability level. Teams that need a large-context multimodal model for lighter reasoning and content tasks will find it cost-effective, but those needing top-tier coding or agentic performance should look to the Grok 4.5 or comparable flagships.

Assessed July 10, 2026

Editorial notes

Grok 4.3 from xAI offers a 1M token context window, vision, tool use, and function calling at competitive pricing, though its intelligence and coding benchmarks sit in the moderate range below the current Grok flagship.

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

Performance Profile

Intelligence3.6Technical4.4Value7.3Content4.1
Intelligence 3.6/10
Technical 4.4/10
Content 4.1/10
Value 7.3/10

How xAI: Grok 4.3 compares

XAI: Grok 4.3 ranks #118 of 392 AI models we track for overall intelligence, #72 of 161 for coding, #118 of 296 for agentic tasks. Its 1M-token context window is larger than 90% of the models we list. At $1.25 per million input tokens it is cheaper than 22% of comparable models.

About xAI: Grok 4.3

Grok 4.3 is a reasoning model from xAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual..

Capabilities

Tool Use Function Calling Vision

Performance Indices

Source: Artificial Analysis

24.8 Intelligence Index
35.2 Coding Index
42.4 Agentic Index

Benchmark Scores

Intelligence

GPQA Diamond 65.8% Graduate-level scientific reasoning
HLE 6.5% Humanity's Last Exam
SciCode 37.4% Scientific computing

Technical

TerminalBench Hard 18.9% Agentic terminal tasks
τ²-Bench 65.8% Conversational agent benchmark

Content

IFBench 47.6% Instruction following
LCR 24.7% Long-context reasoning

Benchmark data from Artificial Analysis and Hugging Face

How does xAI: Grok 4.3 stack up?

Compare side-by-side with other professional models.

Compare Models

Model Information

OpenRouter ID x-ai/grok-4.3
Providerx-ai
Release Date April 30, 2026
Context Length1,000,000 tokens
Status Active

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $1.25 $0.001250
Output $2.50 $0.002500

Live Performance

Live endpoint metrics, refreshed every 30 minutes.

99.6%
Avg Uptime
766ms
Best Latency (TTFT)
92 tok/s
Best Throughput
4/4
Active Endpoints
Available via: xAI

Leaderboard Categories

Frequently asked questions about xAI: Grok 4.3

How much does xAI: Grok 4.3 cost?

xAI: Grok 4.3 costs $1.25 per million input tokens and $2.50 per million output tokens.

What is the context window of xAI: Grok 4.3?

xAI: Grok 4.3 has a context window of 1,000,000 tokens (1M).

Is xAI: Grok 4.3 good for coding?

On our coding benchmark index, xAI: Grok 4.3 ranks #72 of 161 models, placing it in the broader range of the field for code generation and debugging.

What can xAI: Grok 4.3 do?

xAI: Grok 4.3 supports image/vision input, tool use, and function calling.

Who created xAI: Grok 4.3?

xAI: Grok 4.3 is developed by xAI and was released on April 30, 2026.