How much does Grok 4 cost?

Grok 4 costs $3.00 per million input tokens and $15.00 per million output tokens, using the median price across hosting providers as of 26 Oct 2026. That is about $1.05 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?

Grok 4 has a context window of 262K tokens, roughly 197,000 words of text read at once. A single answer can be up to 256K tokens long.

Is Grok 4 open source?

We list Grok 4 as closed: it is used through its maker's apps or API and its weights are not published (Epoch AI lists its access as "API access").

How good is Grok 4 compared with other AI models?

On the Epoch Capabilities Index, Grok 4 scores 146.2 (likely range 144.4 to 148.0), which ranks 78 of 270 models we track. On Arena's human-vote text board it is ranked 97 of 166. Scores close together are a tie in practice.

How does Grok 4 compare with Qwen3.6 27B?

Qwen3.6 27B scores higher on 1 of 3 shared quality measures, Grok 4 on 0. 2 measures are too close to call. Qwen3.6 27B costs about 82% less than Grok 4 on a blended price of $1.08 against $6.00 per million tokens. See the full comparison for every measure.

How current are these numbers for Grok 4?

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: Score, Price and Context Window

Where Grok 4 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 Jul 2025

Its score range overlaps with MiniMax-M2.5, the model just above it, so a small gap in rank is not a meaningful difference.

Skip if

Tight budgets: it is among the priciest quarter of models in the top half by score.

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

Key facts

Overall score: 146.2; Rank 78 of 270. Likely range 144.4 to 148.0.
Human preference: chat: 1411; Rank 97 of 166. 39,679 votes.
Human preference: coding: 1435; Rank 107 of 166. 8,036 votes.
Human preference: images: 1184; Rank 71 of 85. 30,173 votes.
Price per million tokens: $3.00 in / $15.00 out; Blended $6.00. Median across hosting providers, checked 26 Oct 2026.
Context window: 262K tokens; About 197,000 words at once. One answer up to 256K tokens.
Weights: Closed; Used through the maker's apps or API (Epoch AI: API access).

Features listed by the price list: Tool use.

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 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 compared with all models we trackOverall capability: 146.2. Better than 71% of the other 269 models. Human preference: chat: 1411. Better than 41% of the other 165 models. Human preference: coding: 1435. Better than 35% of the other 165 models. Human preference: images: 1184. Better than 16% of the other 84 models. Price: $6.00 per 1M. Cheaper than 12% of the other 200 priced models. Context window: 262K tokens. Larger context window than 50% of the other 198 models.

Overall capability146.2
Better than 71% of the other 269 modelsUpper half
Epoch Capabilities Index: one score that combines many tests.
Human preference: chat1411
Better than 41% of the other 165 models
How often people pick its answers over another model's on Arena.
Human preference: coding1435
Better than 35% of the other 165 models
How often people pick its answers to coding questions on Arena.
Human preference: images1184
Better than 16% of the other 84 models
How often people pick its answers about pictures on Arena.
Price$6.00 per 1M
Cheaper than 12% of the other 200 priced models
Blended price per million tokens. Lower is better, so the cheapest models sit on the right.
Context window262K tokens
Larger context window than 50% of the other 198 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 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.

Aider Polyglot
225 coding exercises in six programming languages. The AI edits the code files and the exercise's tests decide pass or fail.
79.6%
Place 5 of 46
SimpleBench
Everyday common-sense and trick questions that most people answer correctly but AI models often get wrong.
60.5%
Place 25 of 80
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.
87.0%
Place 61 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.
84.0%
Place 80 of 174
ARC-AGI-2
Visual puzzles where the AI must work out a new rule from a few examples and apply it. They test picking up a new idea quickly, not recalling facts.
16.0%
Place 48 of 86
Terminal-Bench
Tasks done in a computer terminal, such as setting up software or fixing a broken build, checked by automatic tests. Scores here use the benchmark's standard reference agent so models are compared on the same footing.
23.1%
Place 21 of 25

What it costs in everyday terms

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

100 chats: $1.05; 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: $0.30; 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: $6.00 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

How much does Grok 4 cost?: Grok 4 costs $3.00 per million input tokens and $15.00 per million output tokens, using the median price across hosting providers as of 26 Oct 2026. That is about $1.05 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?: Grok 4 has a context window of 262K tokens, roughly 197,000 words of text read at once. A single answer can be up to 256K tokens long.
Is Grok 4 open source?: We list Grok 4 as closed: it is used through its maker's apps or API and its weights are not published (Epoch AI lists its access as "API access").
How good is Grok 4 compared with other AI models?: On the Epoch Capabilities Index, Grok 4 scores 146.2 (likely range 144.4 to 148.0), which ranks 78 of 270 models we track. On Arena's human-vote text board it is ranked 97 of 166. Scores close together are a tie in practice.
How does Grok 4 compare with Qwen3.6 27B?: Qwen3.6 27B scores higher on 1 of 3 shared quality measures, Grok 4 on 0. 2 measures are too close to call. Qwen3.6 27B costs about 82% less than Grok 4 on a blended price of $1.08 against $6.00 per million tokens. See the full comparison for every measure.
How current are these numbers for Grok 4?: 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