# Grok 4.3

> Grok 4.3 is available on Artifio.ai — a unified AI workspace with a single pay-as-you-go wallet.

- Canonical page: https://artifio.ai/models/grok-4-3
- Run it: https://artifio.ai/create/grok-4-3
- Modality: prompt to text
- Model brand: xAI
- Pricing: from about $0.150 per generation (exact cost shown in the workspace before you confirm; varies with selected options)
- Typical generation time: ~25s (catalogue estimate)
- Full pricing table: https://artifio.ai/pricing/models

## About Grok 4.3

Grok 4.3 is xAI's high-volume text model, shipped to the xAI API at the end of April 2026 after an April beta for SuperGrok and X Premium+ subscribers. xAI positions it as the fast, reliable workhorse of the lineup, with strong tool calling and instruction following, a 1-million-token context window, and per-token prices well below its predecessor Grok 4.20. It matters beyond its own release: on May 15, 2026, xAI retired a swath of older Grok slugs and redirected their traffic to Grok 4.3.

Independent benchmarking framed it as a price-and-speed play rather than a frontier bid, sitting a step behind the top OpenAI and Anthropic models while undercutting them on cost. On artifio.ai it runs alongside 100+ models in one workspace from a single wallet.

## Features

- 1,000,000-token context window, with a separate higher rate applied to requests beyond 200K tokens.
- Text and image input with text output.
- Configurable reasoning effort across four levels: none, low, medium, and high.
- Function calling and structured outputs, plus server-side web search and X search tools.
- Cached input tokens billed at a fraction of the standard rate.
- Document generation in consumer surfaces: formatted PDF reports, multi-sheet spreadsheets, and slide decks.
- Knowledge cutoff of December 2025 unless search tools are enabled.

## What people use it for

- Agentic pipelines that need many tool calls per task at a low per-token cost.
- Long-document analysis and codebase-scale context work within the 1M-token window.
- High-volume production workloads such as classification, extraction, and summarisation.
- Report, spreadsheet, and slide generation for office-style deliverables.
- Drop-in replacement for retired Grok 3 and Grok 4 era model slugs.

## Reported strengths

- Scored 53 on the Artificial Analysis Intelligence Index, 4 points above Grok 4.20, while cutting input price by roughly 37 percent and output price by roughly 58 percent.
- Jumped 321 Elo on the GDPval-AA agentic benchmark to 1500, passing Gemini 3.1 Pro Preview and Kimi K2.5.
- Strong instruction following: 98 percent on tau-squared-Bench Telecom and 81 percent on IFBench.
- One of the cheapest 1M-context reasoning models on the market at launch.

## Reported limitations

- Hallucination worsened versus its predecessor, dropping 8 points on Artificial Analysis's AA-Omniscience measure.
- Uses about 44 percent more output tokens than Grok 4.20, which claws back part of the headline price cut.
- Trails GPT-5.5 by 276 Elo on GDPval-AA and sits below the frontier tier on the Intelligence Index.
- Requests past 200K context tokens are billed at a higher rate, so the full 1M window costs disproportionately more.

## Sources

1. grok-4.3 model page (xAI Docs): https://docs.x.ai/developers/models/grok-4.3
2. xAI launches Grok 4.3 with improved agentic performance and lower pricing (Artificial Analysis): https://artificialanalysis.ai/articles/xai-launches-grok-4-3-with-improved-agentic-performance-and-lower-pricing
3. xAI launches Grok 4.3 at an aggressively low price and a new, fast, powerful voice cloning suite (VentureBeat): https://venturebeat.com/technology/xai-launches-grok-4-3-at-an-aggressively-low-price-and-a-new-fast-powerful-voice-cloning-suite

---

About Artifio.ai: 100+ AI image, video, and audio models in one workspace with a single shared wallet — no per-model subscriptions. This is the markdown rendition of https://artifio.ai/models/grok-4-3 for AI assistants and crawlers; the HTML page is canonical.