Model by OpenAI

GPT-5.3-Codex

GPT-5.3-Codex is OpenAI's agentic coding model from early 2026, and it now suits only teams that must keep an existing pipeline running.

Checked 2026-11-05

GPT-5.3-Codex is OpenAI's agentic coding model from early 2026, and it now suits only teams that must keep an existing pipeline running. OpenAI's model page lists it as deprecated. The deprecations page shows the announcement on 1 October 2026, shutdown on 1 April 2027, and gpt-6-sol as the recommended replacement. OpenRouter listed the model on 24 February 2026. The context window is 400,000 tokens, of which 272,000 can be input, with up to 128,000 tokens of output and a knowledge cutoff of 31 August 2025. Price is $1.75 per million input tokens and $14 per million output tokens, both matching OpenRouter. The catch is the endpoint: only the Responses API is supported, and Chat Completions and Batch are not. Plan the move well before April 2027, because OpenAI has set that date for shutdown. For new coding work we would start on the GPT-6 line instead; the low price is the only reason to stay. Our GPT codex guide covers what replaced it. Figures come from OpenAI's model page, its deprecations page and OpenRouter. We have not run it ourselves.

Mentioned here

Questions

What is the context window of GPT-5.3-Codex?

400,000 tokens, with up to 128,000 tokens of output.

How much does GPT-5.3-Codex cost?

$1.75 per million input tokens and $14 per million output tokens, checked 31 October 2026.

Can I run GPT-5.3-Codex on my own hardware?

No. The weights are not published, so you use it through the maker's API or a hosting provider.

Who makes GPT-5.3-Codex?

OpenAI makes it, and released it on 24 February 2026.

Reviews

Loading reviews…

Write a review

Your rating

Up to 1000 characters. Stars alone are enough.

Where you can run it

Compare hosts

  • OpenRouter

    OpenRouter routes more than 600 models through one API key.

    • Model gateway (router)
    • OpenAI compatible

Similar

  • GPT-4.1

    GPT-4.1 is OpenAI's April 2025 non-reasoning model, built for instruction following and long-context code work, and it is now deprecated.

    • Closed

    OpenAI, 1M context, $2 in / 1M

  • o3

    o3 is OpenAI's April 2025 reasoning model, and it is now deprecated, so it suits only code that still calls it.

    • Closed

    OpenAI, 200K context, $2 in / 1M

  • gpt-oss-20b

    gpt-oss-20b is OpenAI's smaller open-weights model, suited to running a reasoning model on your own machine or paying very little through an API.

    • Open weights

    OpenAI, 131K context, $0.03 in / 1M

  • GPT-5.4 Nano

    GPT-5.4 Nano was OpenAI's cheapest GPT-5.4 model, built for speed-critical, high-volume jobs, and it is now deprecated.

    • Closed

    OpenAI, 400K context, $0.20 in / 1M

  • GPT-5.4 Mini

    GPT-5.4 Mini is OpenAI's smaller GPT-5.4 model, aimed at high-throughput coding and reasoning work where the full model costs too much.

    • Closed

    OpenAI, 400K context, $0.75 in / 1M

  • GPT-5.4

    GPT-5.4 is an earlier OpenAI frontier model, and it suits teams already on the OpenAI API who need a very long context for coding and document work.

    • Closed

    OpenAI, 1.1M context, $2.50 in / 1M