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
