ZMIME
OpenAI · Released Feb 5, 2026

GPT-5.3 Codex

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

  • Proprietary
  • Reasoning
  • Tool calling
  • Vision
Capability
156.8ECI · #18 of 148
Input
$1.75per 1M tokens
Output
$14.00per 1M tokens
Context
400K128K max output
Pricing

What it costs

Input
$1.75per million tokens
Output
$14.00per million tokens
Cached input
$0.175per million tokens
Blended (3:1)
$4.81pricier than 87% of priced models

Typical monthly bills

Monthly usageEstimated cost
Side project2M input + 0.5M output tokens$10.50
Team assistant25M input + 5M output tokens$113.75
Production app250M input + 50M output tokens$1,138

Official OpenAI API price, as listed on models.dev.

Capability

Independent benchmarks

156.8Epoch Capabilities Index
#18 of 148 scored models
88Median 146167

The shaded band is Epoch AI’s confidence range (153.5–160.8); the tick marks the median scored model.

  • SWE-bench VerifiedFixing real GitHub issues · high setting74.8%

Scores from Epoch AI, run independently of OpenAI.

Specifications

The details

Lab
OpenAI
Released
Feb 5, 2026
Knowledge cutoff
Aug 31, 2025
Context window
400,000 tokens
Max output
128,000 tokens
Inputs
Text, Images, PDFs
Output
Text
Reasoning
Adjustable effort low · medium · high · xhigh
Tool calling
Yes
Structured output
Yes
Weights
Proprietary
API model ID
gpt-5.3-codexon OpenAI
Availability
19 API providerslisted on models.dev

OpenAI model documentation

Lab-reported

What OpenAI claims

Published by the lab at launch. Settings vary, so compare these only with care.

BenchmarkScoreSettingSource
SWE-Atlas Codebase QnA32.6—Source
SWE-Atlas Refactoring42.38—Source
SWE-Atlas Test Writing38.98—Source
Same lab

More from OpenAI

Questions

About GPT-5.3 Codex

How much does GPT-5.3 Codex cost?

GPT-5.3 Codex costs $1.75 input / $14.00 output per million tokens (official OpenAI API price). Cached input is $0.175 per million tokens. At a 3:1 input-to-output mix that is $4.81 per million tokens, more expensive than 87% of the 360 priced models we track.

What is the context window of GPT-5.3 Codex?

GPT-5.3 Codex accepts up to 400,000 tokens per request and can write up to 128,000 tokens in one response.

How good is GPT-5.3 Codex?

Epoch AI gives GPT-5.3 Codex a Capabilities Index score of 156.8 (likely range 153.5–160.8), ranking it #18 of 148 models Epoch has scored. Epoch AI benchmark results: SWE-bench Verified 74.8%.

Is GPT-5.3 Codex open source?

No. GPT-5.3 Codex is proprietary; you use it through OpenAI’s API or partner platforms.

What inputs does GPT-5.3 Codex support?

GPT-5.3 Codex accepts text, images and PDFs and replies in text. It is a reasoning model with low, medium, high and xhigh effort settings, supports tool calling and can return structured JSON output.

When was GPT-5.3 Codex released?

OpenAI released GPT-5.3 Codex on Feb 5, 2026. Its training data runs to Aug 31, 2025.

What are the best alternatives to GPT-5.3 Codex?

The closest current models from other labs on capability, price and release date are Gemini 3.1 Pro Preview (Google, ECI 154.8, $2.00 / $12.00), Claude Sonnet 5 (Anthropic, ECI 156.3, $2.00 / $10.00), Kimi K3 (Moonshot AI, ECI 157.6, $3.00 / $15.00) and Qwen3.8 Max (Alibaba (Qwen), ECI 156.6, $2.00 / $6.00).