Microsoft
Phi-4-mini-instruct is a lightweight open model built upon synthetic data and filtered publicly available websites - with a focus on high-quality, reasoning dense data. The model belongs to the Phi-4...
Running this yourself: consumer gpu should be enough.
Current rates are not verified. Missing pricing does not mean free usage.
No current subscription pricing is tracked for this model.
Confirm this specific model, usage limits, and billing terms with the provider. A subscription does not automatically include API credits.
No login needed to compare. Prices are in USD; provider charges are separate from AI Market Cap plans. Context length, caching, tools, taxes, and regional terms can change the final cost. Open weights do not mean free hosting.
42.2
Quality Score
---
Arena ELO
4B
Parameters
131K
Context
This measures the amount of verifiable public evidence we have, not how capable the model is. A missing field means it has not been verified yet, not that its value is zero.
17 of 22 public signals
Sign in to join the discussion
301.6K
Downloads
891
Likes
Oct 2025
Released
5/5 signals
3/4 signals
4/5 signals
3/4 signals
2/4 signals
Gaps we are still tracking
Launches
4
Benchmarks
21
General
5
Recent launch, pricing, benchmark, and API signals linked to this model or its provider.
Price: $0.131/M tokens | Output: 46.317 tok/s | MMLU: 0.465% | HumanEval: 0.126%
More ways to discover, access, and build with MAI models. MAI models are now available through Vercel, giving developers another way to bring Microsoft AI models into the products and experiences they’re building. This includes our existing MAI models plus today’s newest
View sourcePrice: $0.131/M tokens | Output: 46.317 tok/s | MMLU: 0.465% | HumanEval: 0.126%
View source
MAI-Transcribe-2, the best transcription model in the world, is now generally available in Microsoft Foundry for production use cases! And it’s currently priced at just $0.10 per hour of audio. Come build with it!

More ways to discover, access, and build with MAI models. MAI models are now available through Vercel, giving developers another way to bring Microsoft AI models into the products and experiences they’re building. This includes our existing MAI models plus today’s newest
Price: $0.131/M tokens | Output: 46.29 tok/s | MMLU: 0.465% | HumanEval: 0.126%
Price: $0.131/M tokens | Output: 46.29 tok/s | MMLU: 0.465% | HumanEval: 0.126%
Price: $0.131/M tokens | Output: 46.671 tok/s | MMLU: 0.465% | HumanEval: 0.126%
Price: $0.131/M tokens | Output: 46.782 tok/s | MMLU: 0.465% | HumanEval: 0.126%
Price: $0.131/M tokens | Output: 47.175 tok/s | MMLU: 0.465% | HumanEval: 0.126%
Price: $0.131/M tokens | Output: 47.559 tok/s | MMLU: 0.465% | HumanEval: 0.126%
Price: $0.131/M tokens | Output: 47.273 tok/s | MMLU: 0.465% | HumanEval: 0.126%
Quality: 6.3/100 | Price: $0.131/M tokens | Output: 47.022 tok/s | MMLU: 0.465% | HumanEval: 0.126%
Quality: 6.3/100 | Price: $0.131/M tokens | Output: 47.273 tok/s | MMLU: 0.465% | HumanEval: 0.126%
Quality: 6.3/100 | Price: $0.131/M tokens | Output: 47.367 tok/s | MMLU: 0.465% | HumanEval: 0.126%
Quality: 6.3/100 | Price: $0.131/M tokens | Output: 45.615 tok/s | MMLU: 0.465% | HumanEval: 0.126%
Quality: 6.3/100 | Price: $0.131/M tokens | Output: 46.998 tok/s | MMLU: 0.465% | HumanEval: 0.126%
Quality: 6.3/100 | Price: $0.131/M tokens | Output: 46.215 tok/s | MMLU: 0.465% | HumanEval: 0.126%
Quality: 6.3/100 | Price: $0.131/M tokens | Output: 46.785 tok/s | MMLU: 0.465% | HumanEval: 0.126%
Quality: 6.3/100 | Price: $0.131/M tokens | Output: 46.42 tok/s | MMLU: 0.465% | HumanEval: 0.126%
Quality: 6.3/100 | Price: $0.131/M tokens | Output: 46.131 tok/s | MMLU: 0.465% | HumanEval: 0.126%
Quality: 6.3/100 | Price: $0.131/M tokens | Output: 46.847 tok/s | MMLU: 0.465% | HumanEval: 0.126%
Quality: 6.3/100 | Price: $0.131/M tokens | Output: 47.286 tok/s | MMLU: 0.465% | HumanEval: 0.126%
Quality: 6.3/100 | Price: $0.131/M tokens | Output: 47.436 tok/s | MMLU: 0.465% | HumanEval: 0.126%