GPT-5.3 Codex Spark

gpt-5.3-codex-spark

A GPT model optimized for repository edits, reviews, and agentic software work.

Coding-optimized GPT model for repository edits, reviews, and agentic software work

128K context128K context

Released2026-02-05

Relays17 sites

code generationreasoningtool use

Model information

Model ID: gpt-5.3-codex-spark
Context: 128K
Max input: 100K
Max output: 32K
Knowledge cutoff: 2025-08-31
Open weights: Not supported
License: -
Release date: 2026-02-05

Input

Text: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: SupportedFile: Supported

Output

Text: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported

API capabilities

Reasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Not supported

OpenAI Official Pricing

CNY

Updated: 2026-10-04T22:55:12.873+08:00

Input

~¥11.701/ 1M tokens

Output

~¥93.605/ 1M tokens

Cache read

~¥1.17/ 1M tokens

Relay Comparison

Compare token, per-request, or per-second pricing by relay channel.

Unit: token prices are ¥ / 1M tokens; per-request and per-second rows use their shown unit

sidrune

https://sidrune.ai/Token billing

Price range ¥0.35 - ¥0.875 / 1M tokens

Cache hit¥0.035

Cache hit¥0.0525

GPT-OpenAI官逆

Cache hit¥0.0875

Channel	Billing	Input	Output	Cache hit	Cache write
GPT-Pro	Token	¥0.35	¥2.8	¥0.035	-
GPT-Pro优选	Token	¥0.525	¥4.2	¥0.0525	-
GPT-OpenAI官逆	Token	¥0.875	¥7	¥0.0875	-

云渡

https://yundu.lolToken billing

Price range ¥0.2 - ¥0.4 / 1M tokens

Cache hit¥0.02

Cache hit¥0.03

Cache hit¥0.04

Channel	Billing	Input	Output	Cache hit	Cache write
codex	Token	¥0.2	¥1.9	¥0.02	-
codex-pro	Token	¥0.3	¥2.7	¥0.03	-
Image2	Token	¥0.4	¥3.8	¥0.04	-

找模型

api.zhaomoxing.comToken billing

Price range ¥0.1225 / 1M tokens

Cache hit¥0.0123

Channel	Billing	Input	Output	Cache hit	Cache write
GPT-特惠	Token	¥0.1225	¥0.98	¥0.0123	-

天枢

tian-shu.netToken billing

Price range ¥0.315 - ¥0.525 / 1M tokens

Cache hit¥0.0315

Cache hit¥0.0525

Channel	Billing	Input	Output	Cache hit	Cache write
codex-pro	Token	¥0.315	¥2.52	¥0.0315	-
gpt-pro-stable	Token	¥0.525	¥4.2	¥0.0525	-

天才程序员

gptapis.xyzToken billing

Price range ¥0.21 - ¥0.4025 / 1M tokens

Cache hit¥0.021

不降智应急分组

Cache hit¥0.0315

不降智兜底分组

Cache hit¥0.0403

Channel	Billing	Input	Output	Cache hit	Cache write
不降智	Token	¥0.21	¥1.68	¥0.021	-
不降智应急分组	Token	¥0.315	¥2.52	¥0.0315	-
不降智兜底分组	Token	¥0.4025	¥3.22	¥0.0403	-

Volt

https://voltapi.ai/Token billing

Price range ¥0.2625 - ¥0.6125 / 1M tokens

Codex 超低价

Cache hit¥0.0263

Cache hit¥0.0612

Channel	Billing	Input	Output	Cache hit	Cache write
Codex 超低价	Token	¥0.2625	¥2.1	¥0.0263	-
Codex	Token	¥0.6125	¥4.9	¥0.0612	-

池中鱼

poolai.chatToken billing

Price range ¥0.2975 / 1M tokens

chatgpt pro x20-官冲超稳定满血

Cache hit¥0.0297

Channel	Billing	Input	Output	Cache hit	Cache write
chatgpt pro x20-官冲超稳定满血	Token	¥0.2975	¥2.38	¥0.0297	-

元初AI

ai.yuanc.icuToken billing

Price range ¥1.75 - ¥5.6 / 1M tokens

GPT生图专属分组

Cache hit¥0.175

gemini3.1pro专用

Cache hit¥0.56

Channel	Billing	Input	Output	Cache hit	Cache write
GPT生图专属分组	Token	¥1.75	¥14	¥0.175	-
gemini3.1pro专用	Token	¥5.6	¥44.8	¥0.56	-

Portdan AI

portdan.comToken billing

Price range ¥0.175 / 1M tokens

【余额】Codex 企业级独享

Cache hit¥0.0175

Channel	Billing	Input	Output	Cache hit	Cache write
【余额】Codex 企业级独享	Token	¥0.175	¥1.4	¥0.0175	-

超稳AI中转站

chaowen.asiaToken billing

Price range ¥0.1871 / 1M tokens

ChatGPT-原生不降智【全模型不降】

Cache hit¥0.0187

Channel	Billing	Input	Output	Cache hit	Cache write
ChatGPT-原生不降智【全模型不降】	Token	¥0.1871	¥1.5	¥0.0187	-

How should GPT-5.3 Codex Spark relay pricing be compared?

This GPT-5.3 Codex Spark pricing page compares official pricing with public prices from 17 listed AI gateways. Token prices are shown in CNY per 1M tokens, while per-request, per-second, and per-character rows use the unit shown in the table. Last updated: 11/08/2026, 08:15.

Data sources: Public price catalogs, official pricing records, and monitoring results.
Metric definitions: Uptime means successful probe response rate, fake-rate signals possible model mismatch or abnormal output risk, and latency is average API response time.
Risk note: Relay gateways are third-party services. Pricing, billing, privacy, and stability can change; start with a small top-up and verify reliability before continued use.