Speed
Output tokens / second
GPT-5.3 Codex overview
GPT-5.3 Codex by OpenAI
The most capable agentic coding model ever built, combining frontier coding, deep reasoning, and full computer-use into one model that works with you, not just for you.
GPT-5.3 Codex specs
- Model ID
openai/gpt-5.3-codex- Developer
- OpenAI
- Context window
- 400,000 tokens
- Max output
- 128,000 tokens
- Input
- Text
- Output
- Text
- API
- OpenAI-compatible, base URL
https://api.aimlapi.com/v1
GPT-5.3 Codex API: The Next Generation Agentic Coding Model
Meet GPT‑5.3 Codex, OpenAI’s most advanced agentic coding model for building autonomous, tool‑using developer agents and production‑grade AI workflows. Unlike a simple code autocomplete tool, GPT‑5.3‑Codex can initiate and sustain long-running tasks: conducting research, using external tools, managing deployments, writing documentation, and iterating on complex software over millions of tokens, all while keeping you actively in the loop.
Frontier Coding
Achieves state-of-the-art performance on SWE-Bench Pro, a rigorous, multi-language real-world software engineering benchmark. Resolves complex GitHub issues across Python, JavaScript, TypeScript, Rust, and more.
Advanced Web Development
Builds fully functional, visually polished web apps and games from scratch. GPT‑5.3‑Codex autonomously iterated on complex games over millions of tokens, understanding intent without exhaustive specification.
Research & Analysis
Reads documentation, runs web research, analyzes structured data, and writes comprehensive reports. It can summarize thousands of data points in minutes with concise, actionable insights.
Professional Knowledge Work
Matches GPT‑5.2 on GDPval, OpenAI's benchmark across 44 occupations. Creates presentations, spreadsheets, PRDs, financial analyses, training documents, and more at professional quality.
Setting New Industry Records
GPT‑5.3‑Codex achieves new state-of-the-art results on four benchmarks measuring coding ability, terminal proficiency, computer use, and professional knowledge work.
Use cases
GPT-5.3-Codex is documented as suited to debugging code and fixing failures in software workflows. It is also suited to deploying and monitoring software systems as part of the full software lifecycle. Another documented use case is writing product requirements documents, user research, and editing copy. It is also described as useful for slide decks and analyzing data in spreadsheets.
Capabilities
- Function calling
- Streaming
- Structured outputs
- Reasoning
- Web search
GPT-5.3 Codex benchmarks by 
Artificial Analysis
See how GPT-5.3 Codex compares in generation speed. Data retrieved Nov 3, 2026.
Benchmark results
Compare 17 models available on AI/ML API across 5 independent benchmarks.
Humanity's Last Exam
Expert-written questions across academic subjects.
GPQA Diamond
Graduate-level science questions written to resist web search.
AA-LCR
Reasoning across long documents of about 100k tokens.
IFBench
Following precise instructions about the shape of the answer.
τ²-Bench Telecom
Customer support agent tasks with tool calls.
GPT-5.3 Codex API pricing
| Usage | Price | Unit |
|---|---|---|
| Input | $3.7 | 1M tokens |
| Output | $29.62 | 1M tokens |
| Cached input | $0.3703 | 1M tokens |
Prices from the AI/ML API price list, checked on Nov 4, 2026.
GPT-5.3 Codex vs other models: token prices
AI/ML API input and output rates for 5 models, per million tokens.
| Model | Input | Output |
|---|---|---|
 GPT-5.3 Codex | $3.7 | $29.62 |
| GPT-6 Luna | $0.1 | $0.5 |
| GPT-6.1 Terra | $1 | $5 |
| GPT-6.1 Sol | $2 | $10 |
| GPT-6.1 Terra Pro | $2.12 | $10.58 |
How to use the GPT-5.3 Codex API
View docs
Build with your agent
Give your agent the model details, code and documentation.
Paste it into your coding agent to build the integration.
1Get your API key
Create API keyexport AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"2Make your first request
curl 'https://api.aimlapi.com/v1/chat/completions' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "openai/gpt-5.3-codex",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "openai/gpt-5.3-codex",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}
response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "openai/gpt-5.3-codex",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());Models similar to GPT-5.3 Codex
Related articles
GPT-5.3 Codex FAQ
What is the context window of GPT-5.3 Codex?
GPT-5.3 Codex has a 400,000 tokens context window and can return up to 128,000 tokens.
What inputs and outputs does GPT-5.3 Codex support?
GPT-5.3 Codex takes image, text as input and returns text.
What is the model ID for GPT-5.3 Codex?
Use openai/gpt-5.3-codex as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
When was GPT-5.3 Codex released?
GPT-5.3 Codex became available on March 2, 2026.
How much does GPT-5.3 Codex cost?
GPT-5.3 Codex costs $3.7 input and $29.62 output per 1M tokens on AI/ML API, billed as you go with no subscription.
Does GPT-5.3 Codex support streaming?
Yes, GPT-5.3 Codex can stream responses as they are generated.
Can GPT-5.3 Codex read images?
Yes, GPT-5.3 Codex accepts image input alongside text.
Who created GPT-5.3 Codex?
GPT-5.3 Codex was built by OpenAI.