OpenAI · language model
GPT-5.3-Codex: pricing, context and benchmarks
GPT-5.3-Codex is OpenAI's model released on February 24, 2026. It costs $1.75 per million input tokens and $14 per million output tokens, with a 400K-token context window. Epoch AI ranks it #23 of 125 rated models.
| Performance (ECI) | 33/40 | |
|---|---|---|
| Price | 3/30 | |
| Context | 10/15 | |
| Features | 11/15 |
What you need to know about GPT-5.3-Codex
OpenAI, based in United States, put GPT-5.3-Codex online on February 24, 2026. It accepts text, images, and files as input and produces text. Its context window reaches 400,000 tokens, larger than 64 % of the models in the registry, and it can write up to 128,000 tokens in one go.
It has been available for about 8 months, long enough for its prices and scores to have settled.
GPT-5.3-Codex pricing
On OpenRouter, GPT-5.3-Codex costs $1.75 per million input tokens and $14 per million output tokens. Counting three tokens read for every token written, its average price is $4.813 per million, more expensive than 89 % of paid models (6.3 times the median of $0.76).
A concrete example: a task that sends 2,000 tokens (about 1,500 words) and receives a 500-token answer costs $0.0105. At 1,000 tasks a day, budget $315 a month. The price calculator redoes this with your own volumes.
Tokens already sent and cached are billed at $0.175 per million.
Performance and benchmarks
The Epoch Capabilities Index (ECI), which aggregates published results across many benchmarks, gives GPT-5.3-Codex a score of 157.1 (range 153.6 to 161.4). That places it #23 of 125 rated models.
Scores published by Epoch AI on the benchmarks the site tracks:
| Benchmark | What it measures | Score | Date |
|---|---|---|---|
| SWE-bench Verified | fixing real GitHub issues | 74.8 % | Feb 5, 2026 |
| Terminal-Bench | real tasks in a terminal | 78.4 % | Feb 5, 2026 |
For at least equal performance, Claude Haiku 5.5, Gemini 3.7 Flash, and Kimi K3 cost at least 30% less.
Features, privacy and local use
- It supports tool calling, so it can drive an AI agent, call APIs or MCP servers.
- It can answer in an enforced JSON format (structured outputs).
- It is a reasoning model: it "thinks" before answering, which helps on hard tasks but uses more output tokens.
Its weights are not published: it can only be used through the OpenAI API or a broker such as OpenRouter, which means sending your data off your machines.
Other OpenAI models
| Model | Released | Avg. price | ECI |
|---|---|---|---|
| GPT-6.1 Sol | Sep 29, 2026 | $4 | 168.4 |
| GPT-6.1 Sol Pro | Sep 29, 2026 | $4 | — |
| GPT-6 Sol | Sep 22, 2026 | $4 | 163.7 |
| GPT-6 Luna | Sep 22, 2026 | $0.2 | 156.8 |
| GPT-6 Luna Pro | Sep 22, 2026 | $0.2 | — |
| GPT-6 Sol Pro | Sep 22, 2026 | $4 | — |
| GPT-6 Astra | Sep 4, 2026 | $20 | 168.8 |
| GPT-6 Astra Pro | Sep 4, 2026 | $20 | — |
Verdict
Computed score: 57/100, from public data (performance, price, context, features).
Strengths
- Among the top 20% of models according to Epoch AI (ECI 157.1).
- Agent-ready: tool calling and structured JSON output.
Limitations
- Expensive: costlier than 89 % of paid models.
Avoid if…
- you process large volumes on a tight budget;
- your data must not leave your servers;
- your tasks are mostly simple: a non-reasoning model will cost less.
Alternatives
Comparisons and tools
Learn more
Frequently asked questions
How much does GPT-5.3-Codex cost?
$1.75 per million input tokens and $14 per million output tokens on OpenRouter (checked October 25, 2026). A task with 2,000 tokens read and 500 written costs $0.0105.
How big is GPT-5.3-Codex's context window?
400,000 tokens, roughly 300,000 words, with a maximum of 128,000 output tokens.
Can GPT-5.3-Codex run locally?
No, OpenAI does not publish its weights: it is API-only.
Is GPT-5.3-Codex suitable for an AI agent?
Technically yes: it supports tool calling and structured outputs. Then check its cost for your volume.
How good is GPT-5.3-Codex?
Epoch AI ranks it #23 of 125 rated models (ECI 157.1). On SWE-bench Verified, it scores 74.8%.
What are the alternatives to GPT-5.3-Codex?
The closest models on price and performance are Claude Sonnet 5, Claude Opus 4.7, and Grok 4.6.
Related articles
- Mistral AI: models, pricing and agentsOctober 25, 2026
- LLM benchmarks: how to read model rankingsOctober 24, 2026
- Running a local LLM: hardware, software, and limitationsOctober 24, 2026
- Open-source or closed models for your AI agents?October 5, 2026
Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score