Auto
OpenAI logo

Auto

auto
OpenAI
AIHubMix Smart Router: Fill in the model name as auto, and the gateway will automatically select the optimal model based on the request content; The auto without a suffix uses the default strategy cost_optimized. You can explicitly specify the focus using auto:<strategy>, such as auto (= auto:cost_optimized) cost priority: choose the cheapest as long as the capability meets the standard; auto:balanced balanced: considers capability / cost / latency auto:quality_first quality priority: prioritize selecting the strongest capability for complex reasoning and critical outputs auto:latency_critical low latency priority: prioritize selecting the fastest response

Pricing

Charges are based on the original price of the model actually hit, and the smart routing itself does not charge any additional fees.

Input Modalities

  • Text
  • Vision
  • Audio
  • Video

Output Modalities

  • Text

Capabilities

  • Thinking
  • Web
  • DeepSearch
  • Tools
  • Tool calling
  • Structured outputs
  • Long context

Try this model

Python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AIHUBMIX_API_KEY"],
    base_url="https://aihubmix.com/v1",
)

response = client.chat.completions.create(
    model="auto",
    messages=[
      {
        "role": "user",
        "content": "Hello, how are you?"
      }
    ],
    max_tokens=1024,
    stream=False,
)

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

Frequently asked questions

What is Auto?

AIHubMix Smart Router: Fill in the model name as auto, and the gateway will automatically select the optimal model based on the request content; The auto without a suffix uses the default strategy cost_optimized. You can explicitly specify the focus using auto:<strategy>, such as auto (= auto:cost_optimized) cost priority: choose the cheapest as long as the capability meets the standard; auto:balanced balanced: considers capability / cost / latency auto:quality_first quality priority: prioritize selecting the strongest capability for complex reasoning and critical outputs auto:latency_critical low latency priority: prioritize selecting the fastest response