BazaarLinkBazaarLink
Sign in

GPT 5.3 Codex

GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results...

Intelligence#31 / 563
44
Artificial Analysis Intelligence Index
Speed#149 / 576
94.9
Output tokens per second (median)
Input Price#481 / 576
$1.75NT$ 57
USD / 1M tokens
Output Price#514 / 576
$14.00NT$ 453
USD / 1M tokens
First-token latency#565 / 576
69.67s
Time to first token (AA median)
ProviderOpenAI
Released2026年2月
Model IDopenai/gpt-5.3-codex

Technical specifications

Context window
400K tokens
Reasoning
Yes
Input
TextImageFile
Output
Text

Pricing comparison

BazaarLink retail price alongside AA's observed market standard.

BazaarLink price our site

Input$1.75NT$ 57
Output$14.00NT$ 453
Cache read$0.17NT$ 6
Cache write
3:1 blended (est.)$4.81NT$ 156
All prices per 1M tokens. Supports TWD credit card / official invoice.

Market reference Artificial Analysis

Input$1.75
Output$14.00
Cache readAA not tracked
Cache writeAA not tracked
3:1 blended$4.81
✓ Matches market reference — BazaarLink does not mark up.
Source: artificialanalysis.ai

Independent benchmarks

Scores below come from Artificial Analysis, an independent third party. BazaarLink does not participate in the testing.

Intelligence 44
Coding
Math
MMLU
GPQA 92
This modelCategory leader
Overall intelligence
#31out of 563 models
Aggregated across academic benchmarks
Time to first token
#565out of 576 models
AA 全球 p50:69.67 秒
Intelligence
44
Top 6%
This model
44
Category leader
60
Median
15
GPQA
92%
This model
92%
Category leader
94%
Median
68%
HLE
40%
This model
40%
Category leader
53%
Median
7%
SciCode
53%
This model
53%
Category leader
60%
Median
33%
IFBench
75%
This model
75%
Category leader
83%
Median
44%
τ²-Bench Telecom
86%
This model
86%
Category leader
99%
Median
46%
AA-LCR
74%
This model
74%
Category leader
76%
Median
39%
Terminal-Bench Hard
53%
This model
53%
Category leader
66%
Median
14%

Top 5 — CodingCoding Index leaderboard

1GPT-5.6 Sol (xhigh)openai/gpt-5-6-sol-xhigh78$5 / $30
3GPT-5.6 Sol (high)openai/gpt-5-6-sol-high77$5 / $30
AASource: Artificial Analysis · Independent third-party evaluation; not influenced by BazaarLinkView full evaluation on AA →

Quick Start

Use GPT 5.3 Codex via BazaarLink API — just change the base_url:

Python
from openai import OpenAI

client = OpenAI(
    base_url="https://bazaarlink.ai/api/v1",
    api_key="sk-bl-YOUR_API_KEY",
)

response = client.chat.completions.create(
    model="openai/gpt-5.3-codex",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
TypeScript
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://bazaarlink.ai/api/v1",
  apiKey: "sk-bl-YOUR_API_KEY",
});

const response = await client.chat.completions.create({
  model: "openai/gpt-5.3-codex",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Why use GPT 5.3 Codex via BazaarLink?

  • USD billing (TWD-quoted) + unified invoices — no foreign credit card needed for Taiwan teams
  • OpenAI-compatible API — zero code changes required
  • Automatic failover — multi-provider redundancy for the same model
  • Chinese-language support — local team, instant help
Try Now← All Models

Frequently Asked Questions

What is GPT 5.3 Codex?

GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results...

How much does the GPT 5.3 Codex API cost?

GPT 5.3 Codex costs $1.7500 per 1K input tokens and $14.0000 per 1K output tokens when accessed through BazaarLink.

How do I use GPT 5.3 Codex with the OpenAI SDK?

Set base_url to "https://bazaarlink.ai/api/v1" and use model ID "openai/gpt-5.3-codex". All OpenAI SDK methods (chat.completions, embeddings, streaming) work without code changes.

What is the context window for GPT 5.3 Codex?

GPT 5.3 Codex supports a context window of 400,000 tokens.

Is GPT 5.3 Codex available for free?

GPT 5.3 Codex is a paid model. BazaarLink offers free trial credits on registration so you can test it without a credit card.

中轉站誠信檢測 · BazaarLink 獨家

已測試 endpoint
56
獨立 hosts
41
家族指紋一致率
82%
偵測到異常
47
資料範圍
過去 90

BazaarLink Probe 對聲稱提供此模型的 endpoint 進行家族指紋驗證與 V3 子模型對照。 如發現行為與真貨基準不符,會列入異常案例。

查看完整檢測報告 →

Related Models & Links

More from OpenAI

GPT 4 Turbo PreviewGPT 5.4 MiniGPT 4.1GPT 5.4GPT 5.5o4 Mini Deep Research
All ModelsAPI DocumentationAPI Latency Probe
Support
Support
Hi! How can we help you?
Send a message and we'll get back to you soon.