AI Observatory / Model Radar
Microsoft / microsoft/phi-4
Microsoft: Phi 4
[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...
16,384
Context
16,384
Max output
$0.07 / 1M
Prompt price
2025-01-10
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 | $0.07 / 1M |
| Completion price | $0.14 / 1M | Request price | N/A |
| Context length | 16,384 | Max completion tokens | 16,384 |
| Supported parameters | frequency_penalty, logit_bias, logprobs, max_tokens, min_p, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, top_k, top_logprobs, top_p | ||
Best for
microsoft/phi-4
Microsoft: Phi 4
[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...
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.