How much does Phi-4 cost?

Phi-4 costs $0.098 per million input tokens and $0.32 per million output tokens, using the median price across hosting providers as of 26 Oct 2026. That is about $0.03 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 Phi-4?

Phi-4 has a context window of 16K tokens, roughly 12,000 words of text read at once. A single answer can be up to 16K tokens long.

Is Phi-4 open source?

Phi-4 has open weights: its trained parameters can be downloaded. That is not always the same as open source, because licence terms differ, so read the licence before you use it commercially.

How good is Phi-4 compared with other AI models?

On the Epoch Capabilities Index, Phi-4 scores 130.5 (likely range 124.7 to 132.0), which ranks 157 of 270 models we track. On Arena's human-vote text board it is ranked 155 of 166. Scores close together are a tie in practice.

How does Phi-4 compare with Grok-2 (Dec 2024)?

Phi-4 scores higher on 2 of 3 shared quality measures, Grok-2 (Dec 2024) on 0. 1 measure is too close to call. Phi-4 costs about 96% less than Grok-2 (Dec 2024) on a blended price of $0.15 against $4.00 per million tokens. See the full comparison for every measure.

How current are these numbers for Phi-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

Phi-4: Score, Price and Context Window

Where Phi-4 from Microsoft ranks, what it costs and how much text it can read, in plain numbers with the sources.

Data updated 26 Oct 2026

Microsoft
Open weights
Released Dec 2024

Its score range overlaps with Gemini 1.5 Pro (Sept 2024), the model just above it, so a small gap in rank is not a meaningful difference.

Best for

Running it yourself: its weights can be downloaded (read the licence terms first).

Skip if

Long documents: its context window is only 16K tokens.

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

Key facts

Overall score: 130.5; Rank 157 of 270. Likely range 124.7 to 132.0.
Human preference: chat: 1256; Rank 155 of 166. 24,126 votes.
Human preference: coding: 1306; Rank 149 of 166. 3,305 votes.
Price per million tokens: $0.098 in / $0.32 out; Blended $0.15. Median across hosting providers, checked 26 Oct 2026.
Context window: 16K tokens; About 12,000 words at once. One answer up to 16K tokens.
Weights: Open; The weights can be downloaded. Check the licence before commercial use.

Features listed by the price list: Tool use.

How Phi-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.

Phi-4 compared with all models we trackOverall capability: 130.5. Better than 42% of the other 269 models. Human preference: chat: 1256. Better than 6% of the other 165 models. Human preference: coding: 1306. Better than 10% of the other 165 models. Price: $0.15 per 1M. Cheaper than 89% of the other 200 priced models. Context window: 16K tokens. Larger context window than 6% of the other 198 models.

Overall capability130.5
Better than 42% of the other 269 models
Epoch Capabilities Index: one score that combines many tests.
Human preference: chat1256
Better than 6% of the other 165 models
How often people pick its answers over another model's on Arena.
Human preference: coding1306
Better than 10% of the other 165 models
How often people pick its answers to coding questions on Arena.
Price$0.15 per 1M
Cheaper than 89% of the other 200 priced modelsTop 25%
Blended price per million tokens. Lower is better, so the cheapest models sit on the right.
Context window16K tokens
Larger context window than 6% of the other 198 models
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 Phi-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.

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.
56.1%
Place 128 of 183
tied with 1 other
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.
13.8%
Place 135 of 174

What it costs in everyday terms

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

100 chats: $0.03; 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: less than $0.01; 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: $0.15 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 Phi-4

How much does Phi-4 cost?: Phi-4 costs $0.098 per million input tokens and $0.32 per million output tokens, using the median price across hosting providers as of 26 Oct 2026. That is about $0.03 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 Phi-4?: Phi-4 has a context window of 16K tokens, roughly 12,000 words of text read at once. A single answer can be up to 16K tokens long.
Is Phi-4 open source?: Phi-4 has open weights: its trained parameters can be downloaded. That is not always the same as open source, because licence terms differ, so read the licence before you use it commercially.
How good is Phi-4 compared with other AI models?: On the Epoch Capabilities Index, Phi-4 scores 130.5 (likely range 124.7 to 132.0), which ranks 157 of 270 models we track. On Arena's human-vote text board it is ranked 155 of 166. Scores close together are a tie in practice.
How does Phi-4 compare with Grok-2 (Dec 2024)?: Phi-4 scores higher on 2 of 3 shared quality measures, Grok-2 (Dec 2024) on 0. 1 measure is too close to call. Phi-4 costs about 96% less than Grok-2 (Dec 2024) on a blended price of $0.15 against $4.00 per million tokens. See the full comparison for every measure.
How current are these numbers for Phi-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