AiHubmix-Phi-4-mini-reasoning

by Microsoft

Phi-4-mini-reasoning is a lightweight open model designed for advanced mathematical reasoning and logic-intensive problem-solving. It is particularly well-suited for tasks such as formal proofs, symbolic computation, and solving multi-step word problems. With its efficient architecture, the model balances high-quality reasoning performance with cost-effective deployment, making it ideal for educational applications, embedded tutoring, and lightweight edge or mobile systems. Phi-4-mini-reasoning supports a 128K token context length, enabling it to process and reason over long mathematical problems and proofs. Built on synthetic and high-quality math datasets, the model leverages advanced fine-tuning techniques such as supervised fine-tuning and preference modeling to enhance reasoning capabilities. Its training incorporates safety and alignment protocols, ensuring robust and reliable performance across supported use cases.

API Pricing

Input$0.12 / 1M tokens
Output$0.12 / 1M tokens

Specifications

Context window128,000 tokens
Modalitiestext

FAQ

What is AiHubmix-Phi-4-mini-reasoning?

Phi-4-mini-reasoning is a lightweight open model designed for advanced mathematical reasoning and logic-intensive problem-solving. It is particularly well-suited for tasks such as formal proofs, symbolic computation, and solving multi-step word problems. With its efficient architecture, the model balances high-quality reasoning performance with cost-effective deployment, making it ideal for educational applications, embedded tutoring, and lightweight edge or mobile systems. Phi-4-mini-reasoning supports a 128K token context length, enabling it to process and reason over long mathematical problems and proofs. Built on synthetic and high-quality math datasets, the model leverages advanced fine-tuning techniques such as supervised fine-tuning and preference modeling to enhance reasoning capabilities. Its training incorporates safety and alignment protocols, ensuring robust and reliable performance across supported use cases.

What is the context length of AiHubmix-Phi-4-mini-reasoning?

AiHubmix-Phi-4-mini-reasoning has a 128,000 token context window.

How much does AiHubmix-Phi-4-mini-reasoning cost?

On AIHubMix, AiHubmix-Phi-4-mini-reasoning costs $0.12 per million input tokens and $0.12 per million output tokens.

What modalities does AiHubmix-Phi-4-mini-reasoning support?

AiHubmix-Phi-4-mini-reasoning accepts text input.

How do I call AiHubmix-Phi-4-mini-reasoning via API?

AiHubmix-Phi-4-mini-reasoning 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-Phi-4-mini-reasoning — no other code changes needed.

Who develops AiHubmix-Phi-4-mini-reasoning?

AiHubmix-Phi-4-mini-reasoning is developed by Microsoft. AIHubMix aggregates it alongside models from other providers behind one API and one bill.

More from Microsoft

mai-image-2.5-pro

by Microsoft

MAI-Image-2.5 is Microsoft's flagship AI image generation and editing model. With…

$5/1M in · $5/1M out

mai-image-2.5

by Microsoft

MAI-Image-2.5 is Microsoft's flagship AI image generation and editing model. With…

$5/1M in · $5/1M out

mai-image-2.5-flash

by Microsoft

MAI-Image-2.5 is Microsoft's flagship AI image generation and editing model. With…

$1.75/1M in · $1.75/1M out

aihub-Phi-4-multimodal-instruct

by Microsoft

Microsoft's latest model

$0.12/1M in · $0.48/1M out
128,000 tokens context

aihub-Phi-4-mini-instruct

by Microsoft

Microsoft's latest model

$0.12/1M in · $0.48/1M out
128,000 tokens context

aihub-Phi-4

by Microsoft

Phi-4 is a state-of-the-art open model based on a combination of synthetic datasets…

$0.12/1M in · $0.48/1M out
16,400 tokens context

Use AiHubmix-Phi-4-mini-reasoning via the AIHubMix unified API — one interface for every major LLM.