AI Observatory / Model Radar
Microsoft / microsoft/phi-4-mini-instruct
Microsoft: Phi 4 Mini Instruct
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...
128,000
Context
128,000
Max output
$0.08 / 1M
Prompt price
2025-10-17
Created
01 / Snapshot
Pricing, context, modalities, and parameters.
Model Radar detail pages stay neutral and operator-readable: core metadata first, then workflow fit.
| Provider | Microsoft | Input modalities | text |
|---|---|---|---|
| Output modalities | text | Prompt price | $0.08 / 1M |
| Completion price | $0.35 / 1M | Request price | N/A |
| Context length | 128,000 | Max completion tokens | 128,000 |
| Supported parameters | frequency_penalty, max_tokens, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, top_k, top_p | ||
Best for
microsoft/phi-4-mini-instruct
Microsoft: Phi 4 Mini Instruct
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...
Deep analysis
High-volume usage
low-cost
03 / Colophon
Routes and exits.
Each model page stays simple: overview, compare, related models, then back to the public hub.