OpenAI

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
Relays18 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

~¥11.706/ 1M tokens

Output

~¥93.651/ 1M tokens

Cache read

~¥1.171/ 1M tokens

Relay Comparison

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

sidrune

https://sidrune.ai/Token billing

Price range ¥0.35 - ¥0.875 / 1M tokens

GPT-Pro-余额
BillingToken
Input¥0.35
Output¥2.8
Cache hit¥0.035
Cache write-
GPT-Pro优选-余额
BillingToken
Input¥0.525
Output¥4.2
Cache hit¥0.0525
Cache write-
GPT-OpenAI官Key逆-余额
BillingToken
Input¥0.875
Output¥7
Cache hit¥0.0875
Cache write-

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 18 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: 10/23/2026, 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.