Gpt 5.3 Codex

Name: Gpt 5.3 Codex API
Brand: OpenAI
SKU: gpt-5.3-codex

silvamux/gpt-5.3-codex

GPT-5.3 Codex is a coding-agent model that analyzes, implements, tests and fixes issues around real codebases — built for software teams that want a model to continuously operate in a development environment.

Supported modalities

text

Input price$1.75 / 1M tokensper 1M tokens

Output price$14 / 1M tokensper 1M tokens

Pricing

Tune and Pro share the same prices.

Input context	Input	Output	Cache read	Cache write
-	$1.75 / 1M tokens	$14 / 1M tokens	$0.175 / 1M tokens	$1.75 / 1M tokens

Capabilities

GPT-5.3 Codex scored 72 overall, performing well across the board — a coding-agent model built for real repositories. It stands out in code generation (99%), information retrieval / RAG (92%) and text comprehension (86%), reliably producing working code from a codebase and grounding answers in retrieved documents, which makes it a strong fit for software engineering and enterprise knowledge-base workflows. Comparatively, math and science reasoning (36%) falls short, so quantitative-heavy tasks may need extra verification. The deeper the codebase work, the more value it delivers.

Overall

72/ 100良好

HighlightsCode Generation 99%Information Retrieval / RAG 92% · Text Comprehension 86%

Best forSoftware Engineering / Information Retrieval / Enterprise Knowledge BaseScenario fit 72%

Relative weaknessMath & Science Reasoning36%

Advanced Capabilities

8 items

Agent Collaboration43%

7 questions · Mixed

Code Generation99%

10 questions · Objective

Code Comprehension & Debugging82%

12 questions · Subjective

Creative Writing80%

17 questions · Subjective

Information Retrieval / RAG92%

13 questions · Mixed

Long-Context Handling72%

3 questions · Subjective

Math & Science Reasoning36%

14 questions · Objective

Multilingual Capability76%

10 questions · Mixed

General Foundations

3 items

General Knowledge74%

15 questions · Mixed

Text Comprehension86%

5 questions · Subjective

Logical Reasoning46%

20 questions · Mixed

Safety & Compliance

2 items

Hallucination Control71%

9 questions · Subjective

Instruction Following78%

14 questions · Subjective

Performance

Gpt 5.3 Codex

gpt-5.3-codex

Last 24 hours · 153,904 requests

First token · TTFT · P50: 2370ms
Output speed · TPS · P50: 34tok/s
Full response · E2E · P50: 3.59s
Request success rate: 99.02%

24-hour availability

24 hours ago12 hours agoNow

Gpt 5.3 Codex example code and API

Progpt-5.3-codex

/api/v0/chat/completions/api/v1/responses

UnifiedOpenAI Responses

curl https://silvamux.io/api/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.3-codex",
    "messages": [{"role": "user", "content": "Hello, please introduce yourself"}]
  }'

# pip install openai
from openai import OpenAI

client = OpenAI(
    base_url="https://silvamux.io/api/v1",
    api_key="YOUR_API_KEY",
)

response = client.chat.completions.create(
    model="gpt-5.3-codex",
    messages=[
        {"role": "user", "content": "Hello, please introduce yourself"}
    ],
)

print(response.choices[0].message.content)

// Gradle: implementation(__HL_SLOT_0__)
import okhttp3.*;

OkHttpClient client = new OkHttpClient();
MediaType json = MediaType.get("application/json");
String payload = "{\"model\":\"gpt-5.3-codex\",\"messages\":[{\"role\":\"user\",\"content\":\"Hello, please introduce yourself\"}]}";

Request request = new Request.Builder()
    .url("https://silvamux.io/api/v1/chat/completions")
    .header("Authorization", "Bearer YOUR_API_KEY")
    .post(RequestBody.create(payload, json))
    .build();

try (Response response = client.newCall(request).execute()) {
    System.out.println(response.body().string());
}

// npm install openai
import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'https://silvamux.io/api/v1',
  apiKey: 'YOUR_API_KEY',
})

const response = await client.chat.completions.create({
  model: 'gpt-5.3-codex',
  messages: [{ role: 'user', content: 'Hello, please introduce yourself' }],
})

console.log(response.choices[0].message.content)