AI Model Watch
Models / OpenAI

GPT-5-Codex

Deprecated

Earlier Codex model. Deprecation announced 2026-04-22; shuts down 2026-07-23, replaced by gpt-5.5. Also covers gpt-5.1-codex* per the deprecation table. Context/max-output assumed gpt-5-class; price not captured.

GPT-5-Codex by OpenAI is tracked live in our LLM catalog, with a 400K (400.000-token) context window. It is deprecated, shutting down 23 Jul 2026; the recommended replacement is GPT-5.5.

Last verified: 13 Aug 2026 · sourced from official provider documentation

Lifecycle warning

This model is deprecated. Scheduled shutdown: 23 Jul 2026. Recommended migration: GPT-5.5.

Read the GPT-5-Codex migration guide → replacement & cheapest alternatives

Provider
OpenAI
Status
Deprecated
Input price
—
Output price
—
Cached input
—
Blended price
—
Context window
400.000 tokens (400K)
Max output
128.000 tokens
Modality
text, image
Open weights
No — API only
Knowledge cutoff
—
Released
—
API string
gpt-5-codex

Source: OpenAI official documentation ↗

See also

Explore more

All OpenAI models→

Prices, context windows and lifecycle status for every OpenAI model we track.

Compare models head-to-head→

Side-by-side price, context and status for the models developers weigh against each other.

FAQ

GPT-5-Codex — questions & answers

What is the context window of GPT-5-Codex?

GPT-5-Codex has a 400.000-token context window (400K), with up to 128.000 output tokens per request.

Is GPT-5-Codex being deprecated or retired?

GPT-5-Codex is deprecated. Its scheduled shutdown date is 23 Jul 2026. The recommended migration is GPT-5.5.

Does GPT-5-Codex support image or vision input?

Yes — GPT-5-Codex accepts image input. Listed modalities: text, image.

Can I self-host GPT-5-Codex?

No — GPT-5-Codex is proprietary. Its weights are not publicly released, so it is available only through OpenAI's API (or hosted partners), not for self-hosting.

What is the API model string for GPT-5-Codex?

The API model identifier for GPT-5-Codex is "gpt-5-codex" when calling OpenAI's API.