Loading
Live demos

gpt-5, gpt-5-mini, gpt-5-nano and o3 shut down on 11 December 2026

On 11 December 2026 OpenAI retires gpt-5-2025-08-07, gpt-5-mini-2025-08-07, gpt-5-nano-2025-08-07 (what the gpt-5, gpt-5-mini and gpt-5-nano aliases point to), gpt-5-pro, o3 and o3-pro. The replacements: gpt-5.6-sol (gpt-5, o3), gpt-5.6-terra (mini) and gpt-5.6-luna (nano).

Checked on

gpt-5 OpenAI

Shutdown date: 11 December 2026

Official replacement: gpt-5.6-sol

Price per million tokens (input / output): $1.25 / $10 → $4 / $20

What changes in your code

  • Change the name in model. reasoning_effort (or reasoning.effort) stays and takes none, low, medium (default), high, xhigh and max: start with the level you used, then try one lower.
  • For o1-pro, o3-pro and gpt-5-pro there’s no separate «pro» model: it’s gpt-5.6-sol with reasoning.mode: "pro", Responses API only.
  • max_tokens doesn’t work with reasoning models: use max_completion_tokens or max_output_tokens. OpenAI suggests reserving about 25,000 tokens for reasoning and output when you start.
  • Tools with reasoning: in the Responses API. In Chat Completions, only with reasoning_effort: "none".

Example code

Python
from openai import OpenAI
client = OpenAI()  # reads OPENAI_API_KEY from the environment

resp = client.responses.create(
    model="gpt-5.6-sol",                  # was: "gpt-5"
    reasoning={"effort": "medium"},  # start with the level you used
    max_output_tokens=25000,        # includes reasoning: leave room
    input="Summarise this text…",
)
print(resp.output_text)
Node.js
import OpenAI from "openai";
const client = new OpenAI(); // reads OPENAI_API_KEY from the environment

const resp = await client.responses.create({
  model: "gpt-5.6-sol",                  // was: "gpt-5"
  reasoning: { effort: "medium" }, // start with the level you used
  max_output_tokens: 25000,        // includes reasoning: leave room
  input: "Summarise this text…",
});
console.log(resp.output_text);

Sources: OpenAI · Deprecations · Using GPT-5.6 · Upgrading to GPT-5.6 · Chat Completions API

gpt-5-mini OpenAI

Shutdown date: 11 December 2026

Official replacement: gpt-5.6-terra

Price per million tokens (input / output): $0.25 / $2 → $2 / $12

Sources: OpenAI · Deprecations

gpt-5-nano OpenAI

Shutdown date: 11 December 2026

Official replacement: gpt-5.6-luna

Price per million tokens (input / output): $0.05 / $0.40 → $0.20 / $1.20

Sources: OpenAI · Deprecations

gpt-5-pro OpenAI

Shutdown date: 11 December 2026

Official replacement: gpt-5.6-sol — with reasoning.mode: "pro" (Responses API only)

Sources: OpenAI · Deprecations

Also on this page:

o3 OpenAI

Shutdown date: 11 December 2026

Official replacement: gpt-5.6-sol

Price per million tokens (input / output): $2 / $8 → $4 / $20

Sources: OpenAI · Deprecations

o3-pro OpenAI

Shutdown date: 11 December 2026

Official replacement: gpt-5.6-sol — with reasoning.mode: "pro" (Responses API only)

Sources: OpenAI · Deprecations

We’ll email you before your model is switched off

One email 30 days before and another 7 days before the official date, with the replacement and what changes in the code. Free, no account, no marketing.

Which models does your app use?
More models (38)

Using more than one model? Paste your code into the free checker.

Open the checker

Got a whole repository? Check it at once from the terminal, with nothing to install:

npx -y github:ericc2005t/ai-model-sunset

The code, on GitHub →

Questions

I only use «gpt-5». Am I affected?
Yes: the gpt-5 alias points to gpt-5-2025-08-07, the one being switched off.
Do the parameters change?
Little: they’re still reasoning models. GPT-5.6 adds the xhigh and max levels, and pro mode replaces gpt-5-pro and o3-pro.

Rather I fix it for you? Model swap, €79; full migration, €290–490. I reply within 24 h with a fixed price.

Ask for the fix: I reply within 24 h

No calls and nothing to pay here. Tell me what your app runs on and what breaks: I reply in writing within 24 h with a fixed price and a timeline.

What you need