How much does GPT-5.3 Codex cost?

GPT-5.3 Codex costs $1.75 per million input tokens and $14.00 per million output tokens, using the list price from OpenAI as of 26 Oct 2026. That is about $0.88 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 GPT-5.3 Codex?

GPT-5.3 Codex has a context window of 272K tokens, roughly 204,000 words of text read at once. A single answer can be up to 128K tokens long.

Is GPT-5.3 Codex open source?

We list GPT-5.3 Codex 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 GPT-5.3 Codex compared with other AI models?

On the Epoch Capabilities Index, GPT-5.3 Codex scores 157.1 (likely range 153.6 to 161.4), which ranks 24 of 270 models we track. Scores close together are a tie in practice.

How does GPT-5.3 Codex compare with Kimi K3?

Kimi K3 scores higher on 1 of 2 shared quality measures, GPT-5.3 Codex on 0. 1 measure is too close to call. GPT-5.3 Codex costs about 20% less than Kimi K3 on a blended price of $4.81 against $6.00 per million tokens. See the full comparison for every measure.

How current are these numbers for GPT-5.3 Codex?

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

GPT-5.3 Codex: Score, Price and Context Window

Where GPT-5.3 Codex from OpenAI ranks, what it costs and how much text it can read, in plain numbers with the sources.

Data updated 26 Oct 2026

OpenAI
Closed weights
Released Feb 2026

Its score range overlaps with Muse Spark 1.3, the model just above it, so a small gap in rank is not a meaningful difference.

Best for

Demanding tasks: its overall Epoch score is in the top 10% of models we track.

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: 157.1; Rank 24 of 270. Likely range 153.6 to 161.4.
Human preference: web pages: 1407; Rank 67 of 85. 2,641 votes.
Price per million tokens: $1.75 in / $14.00 out; Blended $4.81. Cached input $0.17. List price from OpenAI, checked 26 Oct 2026.
Context window: 272K tokens; About 204,000 words at once. One answer up to 128K tokens.
Weights: Closed; Used through the maker's apps or API (Epoch AI: API access).

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

We do not have an Arena human-vote rating for GPT-5.3 Codex yet. It is shown as "Not measured" rather than guessed.

Try itChatGPT in our AI tools directoryOpenAI's AI assistant for writing, coding, research, file analysis, and connected work across chats and projects.

How GPT-5.3 Codex 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.

GPT-5.3 Codex compared with all models we trackOverall capability: 157.1. Better than 91% of the other 269 models. Human preference: web pages: 1407. Better than 21% of the other 84 models. Price: $4.81 per 1M. Cheaper than 18% of the other 200 priced models. Context window: 272K tokens. Larger context window than 61% of the other 198 models.

Overall capability157.1
Better than 91% of the other 269 modelsTop 10%
Epoch Capabilities Index: one score that combines many tests.
Human preference: web pages1407
Better than 21% of the other 84 models
How often people pick the web pages and small apps it builds on Arena.
Price$4.81 per 1M
Cheaper than 18% of the other 200 priced models
Blended price per million tokens. Lower is better, so the cheapest models sit on the right.
Context window272K tokens
Larger context window than 61% 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 GPT-5.3 Codex 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.

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.
64.7%
Place 1 of 25
SWE-bench Verified
Real bug reports from open-source software projects. The AI has to change the code so the project's own tests pass. The tasks were checked by people.
74.8%
Place 15 of 32

What it costs in everyday terms

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

100 chats: $0.88; 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: $0.17; 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: $4.81 per 1M; Three parts input to one part output. Our own calculation for comparing models.

Compare GPT-5.3 Codex

Side-by-side pages for the closest rivals.

Similar models

Learn more

Questions about GPT-5.3 Codex

How much does GPT-5.3 Codex cost?: GPT-5.3 Codex costs $1.75 per million input tokens and $14.00 per million output tokens, using the list price from OpenAI as of 26 Oct 2026. That is about $0.88 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 GPT-5.3 Codex?: GPT-5.3 Codex has a context window of 272K tokens, roughly 204,000 words of text read at once. A single answer can be up to 128K tokens long.
Is GPT-5.3 Codex open source?: We list GPT-5.3 Codex 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 GPT-5.3 Codex compared with other AI models?: On the Epoch Capabilities Index, GPT-5.3 Codex scores 157.1 (likely range 153.6 to 161.4), which ranks 24 of 270 models we track. Scores close together are a tie in practice.
How does GPT-5.3 Codex compare with Kimi K3?: Kimi K3 scores higher on 1 of 2 shared quality measures, GPT-5.3 Codex on 0. 1 measure is too close to call. GPT-5.3 Codex costs about 20% less than Kimi K3 on a blended price of $4.81 against $6.00 per million tokens. See the full comparison for every measure.
How current are these numbers for GPT-5.3 Codex?: 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