How much does Grok 4.3 Beta cost?

Grok 4.3 Beta costs $1.25 per million input tokens and $2.50 per million output tokens, using the list price from xAI as of 26 Oct 2026. That is about $0.25 for 100 chats of about 1,000 tokens in and 500 tokens back. Confirm on the maker's site before you buy, because prices change.

What is the context window of Grok 4.3 Beta?

Grok 4.3 Beta has a context window of 1M tokens, roughly 750,000 words of text read at once. A single answer can be up to 1M tokens long.

Is Grok 4.3 Beta open source?

We list Grok 4.3 Beta as closed: it is used through its maker's apps or API and its weights are not published (Epoch AI lists its access as "Hosted access (no API)").

How good is Grok 4.3 Beta compared with other AI models?

On the Epoch Capabilities Index, Grok 4.3 Beta scores 148.8 (likely range 147.2 to 150.3), which ranks 66 of 270 models we track. On Arena's human-vote text board it is ranked 67 of 178. Scores close together are a tie in practice.

How does Grok 4.3 Beta compare with GPT-5.4 Mini?

On quality, neither model leads clearly across the 9 measures both have. 5 measures are too close to call. Their blended prices are similar ($1.56 and $1.69 per million tokens). See the full comparison for every measure.

How current are these numbers for Grok 4.3 Beta?

The newest data on this page is dated 26 Oct 2026. Scores come from Epoch AI and Arena, prices from the open LiteLLM price list.

AI Rankings

Grok 4.3 Beta: Score, Price and Context Window

Where Grok 4.3 Beta from xAI ranks, what it costs and how much text it can read, in plain numbers with the sources.

Data updated 26 Oct 2026

xAI
Closed weights
Released Apr 2026

Its score range overlaps with DeepSeek-V4-Pro, the model just above it, so a small gap in rank is not a meaningful difference.

Best for

Very long documents: its context window is 1M tokens, roughly 750,000 words.

These lines are worked out from the numbers on this page, not from hands-on testing.

Key facts

Overall score: 148.8; Rank 66 of 270. Likely range 147.2 to 150.3.
Human preference: chat: 1442; Rank 67 of 178. 71,348 votes.
Human preference: coding: 1488; Rank 73 of 177. 19,940 votes.
Human preference: web pages: 1358; Rank 78 of 86. 14,970 votes.
Human preference: images: 1242; Rank 51 of 89. 27,901 votes.
Price per million tokens: $1.25 in / $2.50 out; Blended $1.56. Cached input $0.20. List price from xAI, checked 26 Oct 2026.
Context window: 1M tokens; About 750,000 words at once. One answer up to 1M tokens.
Weights: Closed; Used through the maker's apps or API (Epoch AI: Hosted access (no API)).

Features listed by the price list: Image input, Tool use, Reasoning, Web search, Prompt caching, Structured output.

Try itGrok in our AI tools directoryConversational AI assistant for writing, coding, visual creation, and live information from the web and X.

How Grok 4.3 Beta stacks up

Each strip shows every model we track as faint bars. The dot is this model. Better is always to the right, even for price.

Grok 4.3 Beta compared with all models we trackOverall capability: 148.8. Better than 75% of the other 269 models. Human preference: chat: 1442. Better than 62% of the other 177 models. Human preference: coding: 1488. Better than 59% of the other 176 models. Human preference: web pages: 1358. Better than 9% of the other 85 models. Human preference: images: 1242. Better than 43% of the other 88 models. Price: $1.56 per 1M. Cheaper than 42% of the other 199 priced models. Context window: 1M tokens. Larger context window than 72% of the other 197 models.

Overall capability148.8
Better than 75% of the other 269 modelsTop 25%
Epoch Capabilities Index: one score that combines many tests.
Human preference: chat1442
Better than 62% of the other 177 modelsUpper half
How often people pick its answers over another model's on Arena.
Human preference: coding1488
Better than 59% of the other 176 modelsUpper half
How often people pick its answers to coding questions on Arena.
Human preference: web pages1358
Better than 9% of the other 85 models
How often people pick the web pages and small apps it builds on Arena.
Human preference: images1242
Better than 43% of the other 88 models
How often people pick its answers about pictures on Arena.
Price$1.56 per 1M
Cheaper than 42% of the other 199 priced models
Blended price per million tokens. Lower is better, so the cheapest models sit on the right.
Context window1M tokens
Larger context window than 72% of the other 197 modelsUpper half
How much text it can read at once. Bigger suits long documents.

Compared with the other published models that have each measure. Data updated 26 Oct 2026.

Where Grok 4.3 Beta ranks

Leaderboards it appears on, best placing first.

See all leaderboards

Test results

Each test checks one kind of skill. Place shows where it stands among the models that took that test.

GPQA Diamond
Very hard multiple-choice science questions in biology, physics and chemistry, written by experts and designed so a quick web search does not give the answer.
88.8%
Place 48 of 183
OTIS Mock AIME
Maths competition problems in the style of the US AIME exam, from the 2024 and 2025 sets. Every answer is a whole number.
93.3%
Place 47 of 175
tied with 3 others
FrontierMath (Tiers 1-3)
Original, very hard maths problems written by mathematicians. Each has an exact answer and the problems are kept private so models cannot have memorised them. This is the Tiers 1 to 3 set, version 2.
42.8%
Place 58 of 87
SimpleQA Verified
Short factual questions that each have one correct answer. It measures how often a model gets facts right.
33.2%
Place 59 of 82

What it costs in everyday terms

List prices turned into amounts you can picture. Real bills depend on how you use it.

100 chats: $0.25; Cost of 100 chats assumes each chat sends 1,000 tokens (about 750 words) and gets 500 tokens (about 375 words) back.
A 300-page book: $0.13; Cost to read a 300-page book assumes about 100,000 input tokens and no reply. A real book varies with page size and language.
Blended price: $1.56 per 1M; Three parts input to one part output. Our own calculation for comparing models.

Similar models

Models from other makers with a similar overall score.

Learn more

Questions about Grok 4.3 Beta

How much does Grok 4.3 Beta cost?: Grok 4.3 Beta costs $1.25 per million input tokens and $2.50 per million output tokens, using the list price from xAI as of 26 Oct 2026. That is about $0.25 for 100 chats of about 1,000 tokens in and 500 tokens back. Confirm on the maker's site before you buy, because prices change.
What is the context window of Grok 4.3 Beta?: Grok 4.3 Beta has a context window of 1M tokens, roughly 750,000 words of text read at once. A single answer can be up to 1M tokens long.
Is Grok 4.3 Beta open source?: We list Grok 4.3 Beta as closed: it is used through its maker's apps or API and its weights are not published (Epoch AI lists its access as "Hosted access (no API)").
How good is Grok 4.3 Beta compared with other AI models?: On the Epoch Capabilities Index, Grok 4.3 Beta scores 148.8 (likely range 147.2 to 150.3), which ranks 66 of 270 models we track. On Arena's human-vote text board it is ranked 67 of 178. Scores close together are a tie in practice.
How does Grok 4.3 Beta compare with GPT-5.4 Mini?: On quality, neither model leads clearly across the 9 measures both have. 5 measures are too close to call. Their blended prices are similar ($1.56 and $1.69 per million tokens). See the full comparison for every measure.
How current are these numbers for Grok 4.3 Beta?: The newest data on this page is dated 26 Oct 2026. Scores come from Epoch AI and Arena, prices from the open LiteLLM price list.

Where this data comes from

Epoch AI: Benchmark data: Epoch AI, 'Capabilities & benchmarking', epoch.ai/benchmarks (CC BY 4.0). We match models across sources, rank them and show them in charts. Scores are not changed. Epoch AI does not endorse this site.
Arena (formerly LMArena): Human-preference ratings: Arena (arena.ai) leaderboard dataset, CC BY 4.0. We keep the latest published ratings, match them to models from other sources and rank them. Ratings are not changed. Arena does not endorse this site.
LiteLLM model price list: Prices and context windows: LiteLLM model price list (github.com/BerriAI/litellm, MIT licence). We use the model maker's own price entry when there is one. Prices change often, so always confirm on the maker's site before you buy.

Newest data on this page: 26 Oct 2026. Prices are list prices and change often, so confirm on the maker's site before you buy. Sponsors never change a score or an order. How we calculate this · Report a mistake