xAI · Model guide

Grok 4.3

Q: What is Grok 4.3?

Grok 4.3 is available on CrossModel as x-ai/grok-4.3. It has a 1M-token context window and can return up to 1M tokens per request.

Q: How much does Grok 4.3 cost?

Currently $ 1.25 per 1M input tokens and $ 2.50 per 1M output tokens. Cached input is billed at $ 0.20 per 1M.

Q: Does Grok 4.3 support tool calling and structured output?

Tool calling: Supported · Structured output (JSON): Supported · Image input: Supported · Streaming: Supported · Thinking mode: Supported

Q: Which endpoint do I call?

For text models, OpenAI Chat Completions (/v1/chat/completions), OpenAI Responses (/v1/responses) and Anthropic Messages (/v1/messages) all work — pick whichever your SDK already speaks.

Q: Can I try it without writing code?

Yes. Sign in and open the Playground on this page to chat with the model directly — no API key needed. Usage is billed from your wallet at the normal rate.

Compare

x-ai/grok-4.3

A fast, reliable Grok model with a million-token context window and configurable reasoning from none through high. It is a practical fit for long documents, instruction following and tool-driven agents.

Modalities

Context

Max output

Price / 1M tokens

$ 1.25in$ 2.50out

StreamingTool callingJSON outputImage inputThinking mode · can be turned off

What this model is good at

What the vendor positions it for, and which of our models to reach for instead.

VendorA fast model with strong tool calling and instruction following.source

Best for

Large-context workflows · The 1M-token window accommodates large repositories and document sets.source
Tool-assisted knowledge work · xAI highlights instruction following and agentic tool calling as core strengths.(vendor claim)source

Neighbouring models

x-ai/grok-4.5successor —Use Grok 4.5 when coding and higher-end agentic performance matter most.

Compare them side by side →

Pricing and billing

Tiered pricing: the rate changes once the input passes the threshold.

Price / 1M tokens by input size	Input < 200.0K	Input ≥ 200.0K
Input	$ 1.25	$ 2.50
Output	$ 2.50	$ 5.00
Cache read	$ 0.20	$ 0.40
Cache write	$ 1.25	$ 2.50

Estimate a request

Input tokens10,000

Output tokens2,000

Cache hit rate0%

At this input size you are on the Input < 200.0K tier.

$ 0.0175

Estimated cost per request

10.0K × $ 1.25
+ 2.0K × $ 2.50

≈ $ 17.50 per 1,000 requests

Capabilities and limits

What CrossModel guarantees across every route this model can take right now.

Context window: 1.0M tokens
Max output: 1.0M tokens
Input / output modalities: Text + Image → Text
Streaming: Supported
Tool calling: Supported
Structured output (JSON): Supported
Image input: Supported
Thinking mode: Supported· can be turned off
Reasoning effort: none · low · medium · high
Available endpoints: /v1/chat/completions · /v1/responses · /v1/messages

First-party sources:Specsdocs.x.aiCapabilitiesdocs.x.ai 1 docs.x.ai 2

Published benchmarks

Scores the vendor reported, with the evaluation setup each one came from.

Agentic coding

Terminal-Bench 2.1
pass_rate·Artificial Analysis · 2026-08-13effort highsetup not fully disclosed
Artificial Analysis 独立运行；不可与厂商或其他 harness 的成绩直接互换。
39.7%

Coding

SciCode
score·Artificial Analysis · 2026-08-13effort highsetup not fully disclosed
Artificial Analysis 独立评测。
47.3%

Knowledge work

GDPval-AA v2
elo·Artificial Analysis · 2026-08-13effort highsetup not fully disclosed
Artificial Analysis 独立评测；记录页面展示的原始 Elo。
1087.5

Long context

AA-LCR
score·Artificial Analysis · 2026-08-13effort highsetup not fully disclosed
Artificial Analysis 独立长上下文推理评测。
66%

Reasoning

AA Intelligence Index v4.1.1
score·Artificial Analysis · 2026-08-13effort highsetup not fully disclosed
Artificial Analysis 独立评测的九项复合指数，不是百分比；来源页未披露各项完整可复现设置。
37.9
Humanity's Last Exam
accuracy·Artificial Analysis · 2026-08-13effort highsetup not fully disclosed
Artificial Analysis 独立评测。
37.2%

Scientific reasoning

CritPt
score·Artificial Analysis · 2026-08-13effort highsetup not fully disclosed
Artificial Analysis 独立物理推理评测。
8%
GPQA Diamond
accuracy·Artificial Analysis · 2026-08-13effort highsetup not fully disclosed
Artificial Analysis 独立评测。
90.1%

Tool use

tau3-Banking
score·Artificial Analysis · 2026-08-13effort highsetup not fully disclosed
Artificial Analysis 独立评测。
12.4%

Vendor-reported numbers, not CrossModel measurements. Scores are only comparable when the benchmark version, metric and evaluation setup match, so nothing here is averaged or ranked.

Use it in your tools

Point the base URL at CrossModel and paste this model ID — every tool below has a setup guide.

Claude Code

Anthropic's official command-line coding assistant

Cursor

AI-first code editor

Cline

Open-source AI coding agent for VS Code

Codex

OpenAI's coding agent for ChatGPT desktop and the terminal

OpenCode

Open-source terminal coding assistant

Zed

High-performance, AI-native code editor

Open WebUI

Open-source, self-hosted AI chat interface

Continue

Open-source AI coding assistant for VS Code & JetBrains

See all integration guides →

Frequently asked questions

What is Grok 4.3?

Grok 4.3 is available on CrossModel as x-ai/grok-4.3. It has a 1M-token context window and can return up to 1M tokens per request.

How much does Grok 4.3 cost?

Currently $ 1.25 per 1M input tokens and $ 2.50 per 1M output tokens. Cached input is billed at $ 0.20 per 1M.

Does Grok 4.3 support tool calling and structured output?

Tool calling: Supported · Structured output (JSON): Supported · Image input: Supported · Streaming: Supported · Thinking mode: Supported

Which endpoint do I call?

For text models, OpenAI Chat Completions (/v1/chat/completions), OpenAI Responses (/v1/responses) and Anthropic Messages (/v1/messages) all work — pick whichever your SDK already speaks.

Can I try it without writing code?