OpenAI

GPT 5.3 Codex

OpenAIToken-based
Alias:gpt-5.3-codex
Create API Key

Compare gpt-5.3-codex API pricing, supported endpoints, capabilities and access options on Modelsell.

textimagestreamingfunction_callingtoolsstructured_outputjson_modevisionweb_searchcachingreasoningcontext:400000
Starting price
Input / Output · 1M
Context
400K
Maximum input window
Max output
128K
Maximum tokens per response
Modalities
→
Knowledge cutoff
Aug 2025
Released
Feb 2026

Pricing by Supplier

GPT特价
-90%
适合vibe coding自用,gpt pro 号池
Input$1.75$0.175/ 1M
Output$14$1.4/ 1M
Cache Read$0.175$0.0175/ 1M

Capabilities / Supported modalities

StreamingFunction callingToolsStructured outputVisionWeb searchPrompt cachingReasoning
Input
Output

Provider & data privacy

Provider
OpenAIDocs
Tokenizer
o200k_base
License
Proprietary (commercial)Proprietary
Data retention30 daysNot used for upstream training by default

Performance

Benchmarks

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows

Metrics sourced fromArtificial Analysis 2026-09-30·GPT 5.3 Codex

This model is not included in the current benchmark snapshot.

Missing models or measurements are not zero scores.

Benchmark charts preserve the source model selection and reasoning settings. Missing models or measurements are not zero scores, and benchmark cost or speed is not this site’s service commitment.

About GPT 5.3 Codex

围绕真实项目持续推进开发

GPT-5.3-Codex 面向能够读取文件、编辑代码和运行命令的开发环境。它适合从一项工程目标出发,理解已有实现,拆解需要修改的部分,再依据测试与运行反馈调整代码。开发新功能、修复跨文件缺陷、补充测试和整理技术债,都是它可以参与的工作。

给它一个仓库时,目录结构、项目约定和完成标准很重要。例如,“为订单导出增加筛选条件”应同时说明接口行为、权限边界、现有格式以及如何验收。模型可以据此查找相关代码、追踪数据流并安排改动,避免只生成一段脱离项目的示例。

它支持图片输入,页面截图或设计稿可以帮助说明 UI 问题;输出仍然是文字和代码。若要求调整界面,最好提供目标截图、已有组件和交互要求,并在运行页面后检查实际效果。对于后端故障,复现步骤、日志与失败测试通常比一句错误描述更有帮助。

GPT-5.3-Codex 通过 Responses API 使用,支持函数调用、结构化输出和多档推理强度。开发环境需要真实提供文件与命令工具,模型才能执行修改和测试。可以把简单局部任务设为较低推理强度,为复杂依赖分析与架构修改预留更多思考预算。

开发者关心的问题

发一句“修复项目”就够了吗? 建议先给出具体错误、预期结果和可修改范围;明确目标能减少无关重构。

怎样判断任务已经完成? 查看实际差异、测试结果和运行验证。让它在结束时说明修改了什么、执行了哪些检查,以及仍有什么限制,方便代码审阅。

Use cases and prompting

把工程任务写成可验收请求

提供项目环境与验证方式,让模型在同一任务中完成定位、修改和检查。

请修复订单列表切换筛选后偶尔显示旧数据的问题。
先阅读请求状态管理和相关测试,复现快速切换筛选的场景,再给出最小修复。
保留现有接口和页面样式,不做无关重构。
补充能覆盖请求乱序的测试,运行相关检查,并总结改动与验证结果。

接入时选择 Responses API,并提供所需工具。若只允许分析,请明确禁止写文件;若允许修改,写清目录、命令和完成标准。持续任务应保留关键约束与已完成的验证记录,方便后续工作衔接。

API access

API documentation

Code samples

RequestPOST/v1/chat/completions
Example request
Parameters
ParameterTypeDefault / rangeDescription
temperature
number
=10 ~ 2
Sampling temperature; lower is more deterministic
top_p
number
=10 ~ 1
Nucleus sampling probability mass
max_tokens
integer>= 1Maximum number of tokens in the response
frequency_penalty
number
=0-2 ~ 2
Penalises repetition of frequent tokens
presence_penalty
number
=0-2 ~ 2
Encourages introducing new topics
stop
array—Up to 4 strings that stop generation
seed
integer—Deterministic sampling seed (best-effort)
n
integer
=1>= 1
Number of completions to generate
stream
boolean
=false
Stream tokens via Server-Sent Events
response_format
object—Force JSON object or schema-conforming output
tools
array—Tool / function declarations the model may call
tool_choice
string
autononerequired
Tool-choice policy or specific tool name
logprobs
boolean
=false
Return per-token log probabilities
top_logprobs
integer0 ~ 20Number of top log probabilities returned per token
logit_bias
object—Per-token logit bias map
user
string—End-user identifier for abuse monitoring

Replace <YOUR_API_KEY> with the API key from your token settings.

Authentication

All requests must include Authorization: Bearer <TOKEN> header. Anthropic-formatted endpoints accept the x-api-key header instead.

Generate tokens from the Tokens page; you can scope them to specific models, groups, IPs, and rate-limits.

Supported parameters

Generation parameters
ParameterTypeDefault / rangeDescription
temperature
number
=10 ~ 2
Sampling temperature; lower is more deterministic
top_p
number
=10 ~ 1
Nucleus sampling probability mass
max_tokens
integer>= 1Maximum number of tokens in the response
frequency_penalty
number
=0-2 ~ 2
Penalises repetition of frequent tokens
presence_penalty
number
=0-2 ~ 2
Encourages introducing new topics
stop
array—Up to 4 strings that stop generation
seed
integer—Deterministic sampling seed (best-effort)
n
integer
=1>= 1
Number of completions to generate
stream
boolean
=false
Stream tokens via Server-Sent Events
response_format
object—Force JSON object or schema-conforming output
tools
array—Tool / function declarations the model may call
tool_choice
string
autononerequired
Tool-choice policy or specific tool name
logprobs
boolean
=false
Return per-token log probabilities
top_logprobs
integer0 ~ 20Number of top log probabilities returned per token
logit_bias
object—Per-token logit bias map
user
string—End-user identifier for abuse monitoring

Rate limits

SupplierRPMTPMRPD
defaultUnlimitedUnlimitedUnlimited
GPT特价UnlimitedUnlimitedUnlimited

No restriction

Frequently asked questions about gpt-5.3-codex

What is gpt-5.3-codex?

Compare gpt-5.3-codex API pricing, supported endpoints, capabilities and access options on Modelsell.

How do I call gpt-5.3-codex?

Create an API key with access to gpt-5.3-codex, then use the exact model ID and a supported endpoint from the API access section. Request fields depend on the selected endpoint.

How is gpt-5.3-codex priced?

Pricing depends on the selected provider group and the model billing unit. The current input, output, request, or media prices are shown on this page before sign-up.

What is the context window of gpt-5.3-codex?

The model catalog lists a context window of 400000 tokens. Check the selected endpoint for request limits.

What is the maximum output of gpt-5.3-codex?

The model catalog lists a maximum output of 128000 tokens. Your request settings may set a lower limit.

How should I evaluate gpt-5.3-codex for my project?

Start with the use cases and prompting guidance on this page, then evaluate the model with representative inputs from your project.