← Back to model catalog
OpenAI

GPT-5.3 Codex

gpt-5.3-codex
Guru+flagship

GPT-5.3 Codex is a flagship model in the Majestix lineup built for coding, agentic, tool use workloads, with 400K context and $1.75 / $14.00 per 1M tokens.

Context Window
400K
Max Output
128K
Pricing
$1.75 input / $14.00 output per 1M tokens

What this model is good at

CodingAgenticTool UseDebugging

Benchmarks and operating signals

SignalValueNote
Context Window400Kplatform limit
Max Output128Kplatform limit
Output Price$14.00 / 1MMajestix pricing

Quick guidance

Use GPT-5.3 Codex when your workload lines up with coding and agentic and you want a clear price-to-capability tradeoff inside Majestix.

This card intentionally focuses on platform context: pricing, limits, and where the model already appears in swarm templates. It is not a self-hosting guide or a vendor deployment manual.

If you want the narrative version, the paired blog intro is the fastest way to explain this model to customers, internal operators, or community readers.