Skip to content
All systems operationalStatus
ChatGPT · OpenAIBalanced tierLatest

GPT-5 mini

gpt-5-mini

A faster, cost-efficient GPT-5 for well-defined tasks.

Get an API key Use it in Codex

Specs & rates

Context window
131K
131,072 tokens
Input
$1.30
per 1M tokens
Output
$6.00
per 1M tokens
Cached input
$1.30
per 1M tokens
Cache write · 5m
$1.30
per 1M tokens
Cache write · 1h
$1.30
per 1M tokens

Use GPT-5 mini

Native endpoint: /v1/responses. Also available on /v1/chat/completions.

# ~/.codex/config.toml
model = "gpt-5-mini"
model_provider = "evolved"

[model_providers.evolved]
name = "evolved.to"
base_url = "https://api.evolved.to/v1"
env_key = "EVOLVED_API_KEY"
wire_api = "responses"
curl https://api.evolved.to/v1/chat/completions \
  -H "Authorization: Bearer $EVOLVED_API_KEY" \
  -H "content-type: application/json" \
  -d '{
    "model": "gpt-5-mini",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.evolved.to/v1",
    api_key=os.environ["EVOLVED_API_KEY"],
)

response = client.responses.create(
    model="gpt-5-mini",
    input="Hello!",
)

print(response.output_text)
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.evolved.to/v1",
  apiKey: process.env.EVOLVED_API_KEY,
});

const response = await client.responses.create({
  model: "gpt-5-mini",
  input: "Hello!",
});

console.log(response.output_text);