Microsoft-Decision-1 reads the content you send and returns a probability for each of a fixed set of answer options instead of writing text. Use it where a pick-one call drives your app: sorting tickets, routing requests, checking an answer, or deciding whether to act, wait or flag the case for a person. It reads about 33 pages at once. It cannot chat, translate or summarize, so pair it with a text model for those jobs.
Phi 4 Mini Instruct
by MicrosoftReleased 17 October 2025
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...
Reads about 130 pages · writes up to 120 pages
Parameters you can send
Standard OpenAI fields, grouped by what they control. Anything not listed is accepted and ignored.
Shaping the reply
How long, how varied, where to stop.
max_tokenstemperaturetop_ptop_kstopseedfrequency_penaltypresence_penaltyrepetition_penaltylogprobstop_logprobsStructured output
Get JSON you can parse instead of prose.
response_formatstructured_outputsQuestions about Phi 4 Mini Instruct
Is Phi 4 Mini Instruct still on sale?
No. Microsoft has retired it. Other Microsoft models are on sale.
What is Phi 4 Mini Instruct best for?
The lab has not said.
Does Phi 4 Mini Instruct work in Arabic, French or Darja?
Microsoft names no languages for Phi 4 Mini Instruct. Arabic, French and Darja: not stated.
Can it read PDFs, images or a whole book?
It reads text. Up to 131K tokens in one request, about 130 pages. It writes up to 96 000 words at once.
Is Phi 4 Mini Instruct open source?
Yes, its weights are public. Open weights on Hugging Face
Who makes Phi 4 Mini Instruct, and when was it released?
Microsoft. Released 17 October 2025.
Other Microsoft models, priced in dinars
See all Microsoft modelsThe low-latency text-to-speech from Microsoft AI for real-time voice, producing expressive speech in 23 languages for voice agents, assistants and call centres, where the full MAI-Voice-2.1 gives up speed for fidelity
#1 for realistic voice · MAI-Voice-2 turns text into speech and returns audio, with control over tone and delivery and a way to give different lines to different speakers. It covers 15 languages in 18 regional versions and offers four ready voices: US English, Mexican Spanish, French and German. Choose it for narration, tutorials and assistants where natural delivery counts more than speed.
Microsoft AI's speech recognition for captions, call records, subtitles and accessibility, reliable across 43 languages, many accents and noisy real-world audio, faster than version 1 on long files but without speaker labels