aihubmix-router

by OpenAI

New model routing capability; request aihubmix-router to automatically route models based on question complexity, so everyone no longer needs to manually switch models; in our tests comparing the use of the model router versus only using GPT-4.1, we observed up to 60% cost savings while maintaining similar accuracy. The context length of the model router depends on the base model used for each prompt. Input size is 200,000, output size is 32,768. Currently, there are four routing models: gpt-4.1, gpt-4.1-mini, gpt-4.1-nano, o4-mini. Pricing: Due to our current billing structure system, requests through aihubmix-router are billed at the price of gpt-4.1-mini regardless of which final model is used; future billing will be based on the actual model invoked. Everyone is welcome to try it out; the interface will return the name of the actual called model.

API Pricing

Input$0.4 / 1M tokens
Output$1.6 / 1M tokens
Cache read$0.1 / 1M tokens

Specifications

Modalitiestext, image

FAQ

What is aihubmix-router?

New model routing capability; request aihubmix-router to automatically route models based on question complexity, so everyone no longer needs to manually switch models; in our tests comparing the use of the model router versus only using GPT-4.1, we observed up to 60% cost savings while maintaining similar accuracy. The context length of the model router depends on the base model used for each prompt. Input size is 200,000, output size is 32,768. Currently, there are four routing models: gpt-4.1, gpt-4.1-mini, gpt-4.1-nano, o4-mini. Pricing: Due to our current billing structure system, requests through aihubmix-router are billed at the price of gpt-4.1-mini regardless of which final model is used; future billing will be based on the actual model invoked. Everyone is welcome to try it out; the interface will return the name of the actual called model.

How much does aihubmix-router cost?

On AIHubMix, aihubmix-router costs $0.4 per million input tokens and $1.6 per million output tokens. Cached input reads are billed at $0.1 per million tokens.

What modalities does aihubmix-router support?

aihubmix-router accepts text and image input.

How do I call aihubmix-router via API?

aihubmix-router is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to aihubmix-router — no other code changes needed.

Who develops aihubmix-router?

aihubmix-router is developed by OpenAI. AIHubMix aggregates it alongside models from other providers behind one API and one bill.

More from OpenAI

gpt-5.6-luna

by OpenAI

GPT-5.6 Luna is designed for cost-sensitive, high-volume workloads. It roughly…

$0.2/1M in · $1.2/1M out
1,050,000 tokens context

gpt-5.6-sol

by OpenAI

GPT‑5.6 Sol sets a new standard for both intelligence and efficiency, achieving…

$5/1M in · $30/1M out
1,050,000 tokens context

gpt-5.6-terra

by OpenAI

GPT-5.6 Terra is designed for workloads that balance intelligence and cost. It roughly…

$2/1M in · $12/1M out
1,050,000 tokens context

gpt-4o-transcribe-diarize

by OpenAI

GPT-4o Transcribe Diarize is an automatic speech recognition (ASR) model with built-in…

$2.5/1M in · $10/1M out
16,000 tokens context

gpt-audio-1.5

by OpenAI

The gpt-audio model is OpenAI's first officially released (generally available) audio…

$2.5/1M in · $10/1M out
128,000 tokens context

gpt-image-2

by OpenAI

GPT-image-2 is OpenAI's latest cutting-edge image generation model. Key value adds…

$5/1M in · $30/1M out

Use aihubmix-router via the AIHubMix unified API — one interface for every major LLM.