codex-mini-latest to gpt-5-codex-mini
Some values not published Checked 2026-10-17.
Price per 1M tokens
| Field | Old | New | Change |
|---|---|---|---|
| Input | $1.5 | Not published | Not published |
| Output | $6 | Not published | Not published |
| Cached input | $0.375 | Not published | Not published |
| Example monthly cost | $27 | Not published | Example only |
Context and max output
| Limit | Old | New | Change |
|---|---|---|---|
| Context window | 200,000 | Not published | Not published |
| Max output | 100,000 | Not published | Not published |
Capabilities that differ
No differing capability values are published for both models.
API changes
No parameter change is listed on the official pages we checked. The sample below only swaps the model id.
Code
python before
from openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
model="codex-mini-latest",
messages=[{"role": "user", "content": "Hello"}],
)
python after
from openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
model="gpt-5-codex-mini",
messages=[{"role": "user", "content": "Hello"}],
)
typescript before
import OpenAI from "openai";
const client = new OpenAI();
const response = await client.chat.completions.create({
model: "codex-mini-latest",
messages: [{ role: "user", content: "Hello" }],
});
typescript after
import OpenAI from "openai";
const client = new OpenAI();
const response = await client.chat.completions.create({
model: "gpt-5-codex-mini",
messages: [{ role: "user", content: "Hello" }],
});
curl before
curl https://api.openai.com/v1/chat/completions \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"codex-mini-latest","messages":[{"role":"user","content":"Hello"}]}'
curl after
curl https://api.openai.com/v1/chat/completions \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"gpt-5-codex-mini","messages":[{"role":"user","content":"Hello"}]}'
Checklist
- Read the shutdown date for codex-mini-latest on the linked official page.
- Point your requests at gpt-5-codex-mini.
- Re-check price, context, and parameters on the provider pages linked here.
- Ship the change before the published shutdown date.