GPT-5 mini

GPT-5 mini is the smaller, faster sibling in OpenAI's GPT-5 generation, designed to deliver most of GPT-5's quality at lower latency and cost. It retains strong reasoning, coding, and structured-output behavior while being suited for high-volume traffic. Use it for chat backends, classification, RAG over moderate context, and any production path where GPT-5-tier quality is overkill.

Quick start

Use any OpenAI-compatible client. Just change base_url and your key.

from openai import OpenAI

client = OpenAI(
    api_key="tl-xxxxxxxxxxxxxxxxxxxxxxxx",
    base_url="https://api.thalam.ai/v1",
)

response = client.chat.completions.create(
    model="openai/gpt-5-mini",
    messages=[
        {"role": "user", "content": "Hello from Thalam!"}
    ],
)

print(response.choices[0].message.content)