---
id: "openai/gpt-5.3-codex"
also: ["openai/gpt-5.3-codex-20260224", "requesty/openai/gpt-5.3-codex", "vercel/openai/gpt-5.3-codex"]
card_usd_per_m: "1.75 in, 14.0 out, at openai"
cheapest_list_usd_per_m: "1.75 in, 14.0 out, at azure on openrouter"
cheapest_effective_usd_per_m: "0.3044 in, 14.0 out, at openai on requesty"
context: 400000
max_output: 128000
input: ["text", "image", "file"]
output: ["text"]
released: "2026-02-24"
reasoning: ["xhigh", "high", "medium", "low", "none"]
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "reasoning_effort", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "verbosity"]
endpoints: 9
gateways: "openrouter (4), requesty (3), vercel (2)"
no_training: 8
trains: 0
retains_prompts: 4
---
# OpenAI: GPT-5.3-Codex

GPT-5.3-Codex advances both the frontier coding performance of GPT‑5.2-Codex and the reasoning and professional knowledge capabilities of GPT‑5.2, together in one model, which is also 25% faster. This enables it to take on long-running tasks that involve research, tool use, and complex execution.