CrossModel
Back to model catalog

xAI · Model guide

Grok 4.3

x-ai/grok-4.3
Modalities
TextImageText
Context
1M
Max output
1M
Grok 4.3

A 1M-context workhorse with reasoning you can switch off

Context window
1M
1,000,000 tokens
Max output
1M
1,000,000 tokens
Released
2026-04
Long-context workhorse
Long context
Whole repos, long documents, multi-file histories
Reasoning off/on
none for latency, high for deep reasoning
Vision + Live Search
Image input and real-time retrieval

Positioned below the Grok 4.5 flagship, trading peak reasoning for a larger window and lower cost.

Overview

Grok 4.3 is xAI's long-context workhorse in the Grok 4 line, released on April 17, 2026. It pairs a very large 1M-token window with an adjustable reasoning control that includes a none setting, so the same model can run as a fast, non-reasoning responder or as a deliberate step-by-step reasoner depending on the request.

Positioned below the newer Grok 4.5 flagship, 4.3 trades a little peak reasoning for a much larger context window and lower cost, which makes it a practical default for whole-repository work, long documents, and high-volume tool loops. Like the rest of the family, it is reachable through an OpenAI-compatible API with native function calling, vision, and Live Search.

Key capabilities

DimensionDetail
Context window1,000,000 tokens
Max output1,000,000 tokens
Input modalitiesText, image
Output modalitiesText
ReasoningAdjustable effort: none / low / medium / high
Toolsfunction calling, structured outputs, streaming, vision, Live Search

Inputs above 200K tokens enter a higher long-context tier (2x pricing). Cached input is billed well below fresh input. See live pricing in the model catalog.

Long context and reasoning modes

Context & Modes

One knob covers cheap throughput and careful reasoning

Reasoning modes
4
none / low / medium / high
Long-context tier
inputs >200K tokens
Max output
1M
no separate output cap

Use none for latency-sensitive volume; turn up to high when a task needs verified multi-step work.

The 1M-token window is the headline: entire codebases, long contract sets, research corpora, and multi-file histories fit in a single request, and the 1M max-output ceiling means large generated artifacts are not truncated by a separate output cap.

The none effort setting is what makes 4.3 versatile. Turn reasoning off for latency-sensitive, high-volume calls where a direct answer is enough; turn it up to high when a task needs verified multi-step work. That one knob lets a single deployment cover both cheap throughput and careful reasoning.

Benchmarks

Benchmarks

Reasoning-first: math, science, and agentic tool use

AIME
95
GPQA Diamond
90.1%
τ²-Bench
97.7%
SWE-Bench
75

xAI's published benchmarks; competition math is near-perfect, and τ²-Bench reflects stable multi-step tool use.

Grok 4.3 is a reasoning-first model, and xAI's published numbers lean that way: 95 on AIME (near-perfect competition math), 90.1% on GPQA Diamond (graduate-level science), and 97.7% on τ²-Bench, which measures stable multi-step tool use across agent loops. On engineering it posts 75 on SWE-Bench and 47.3% on SciCode. Where Grok 4.5's launch leads with agentic coding and token efficiency, 4.3's strength is consistent reasoning and tool use — delivered while keeping a million tokens of context in view.

When to use it

  • Whole-repository work: large codebases, logs, and design docs in one window.
  • Long-document analysis: contracts, research packets, and multi-file corpora.
  • Latency-sensitive volume: turn reasoning to none for fast, cheap direct answers.
  • Cost-aware agents: long tool loops where context size matters more than peak reasoning.

CrossModel exposes Grok 4.3 through an OpenAI-compatible /v1/chat/completions API. Current pricing is available in the model catalog.