GPT-5.3-Codex
Shutting down. GPT-5.3-Codex shuts down on the OpenAI API on Apr 1, 2027. OpenAI names GPT-6 Sol as the replacement.
6 mo- Next shutdown
- 169 daysApr 1, 2027 · OpenAI API
- SWE-bench Verified
- 74.8%#12 of 28 · Epoch AI
- List price · $ per 1M
- $1.75 in $14.00 outOpenAI API · cached input $0.175
- Context window
- 400KMax output 128K tokens
- Released
- Feb 24, 2026OpenAI
Dates on every platform
2 listings · a floor is the earliest possible date
| Platform | Model ID and status | Deprecated | Shuts down | Replacement |
|---|---|---|---|---|
| OpenAI APIOpenAI: Deprecations (opens in a new tab) · checked Oct 14, 2026 | gpt-5.3-codexDeprecated | 6 mo | GPT-6 Sol | |
| Azure AI FoundryMicrosoft: Model retirement schedule - Microsoft Foundry (opens in a new tab) · checked Oct 14, 2026 | gpt-5.3-codex:2026-02-24Active | – | 10 mo | – |
Not available in Chat Completions.
What breaks when you move off GPT-5.3-Codex
- Parameters
- Tooling
Intelligence
Third-party results, credited below
| Benchmark | Publisher | Score | Rank | Published |
|---|---|---|---|---|
| SWE-bench Verified | Epoch AI | 74.8% ± 2.0% | #12 of 28 | Feb 25, 2026 |
Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource].
List prices
$ per 1M tokens, with each price’s source
| Platform | Input | Cached | Output | In effect | Source |
|---|---|---|---|---|---|
OpenAI APIgpt-5.3-codex | $1.75 | $0.175 | $14.00 | Oct 14, 2026Current · Fast mode bills more. | OpenAI: Pricing (opens in a new tab) |
Azure AI Foundrygpt-5.3-codex:2026-02-24 | $1.75 | $0.175 | $14.00 | Mar 1, 2026Current · Global Standard rate from the US East 2 price list. | Microsoft: Azure Retail Prices API (Foundry Models, US East 2) (opens in a new tab) |
Change history
ShutdownGPT-5.1, GPT-5.3-Codex and GPT-5.4 nano shut down on the OpenAI APIOpenAI API2 breaks
OpenAI removes gpt-5.1, gpt-5.3-codex and gpt-5.4-nano. It recommends GPT-6 Sol for GPT-5.1 and GPT-5.3-Codex, and GPT-6 Luna for GPT-5.4 nano.
- Platform
- OpenAI API
- Models
- GPT-5.1, GPT-5.3-Codex, GPT-5.4 nano
- Announced
- ParametersWhen reasoning effort is not none, remove temperature, top_p and top_logprobs. Chat Completions requests must also drop logprobs.
- ToolingGPT-6 Sol and GPT-6 Luna support function calling in Chat Completions only with reasoning_effort none. Use the Responses API for reasoning with tools.
Source: OpenAI, Deprecations (opens in a new tab); OpenAI, Using GPT-6 (opens in a new tab)