phi-4-reasoning-plus
Provider: Azure, Context: 32000, Output Limit: 4096
| Provider | Source | Input Price ($/1M) | Output Price ($/1M) | Description | Free |
|---|---|---|---|---|---|
| azure | models-dev | Input: $0.13 | Output: $0.50 | Provider: Azure, Context: 32000, Output Limit: 4096 | |
| azurecognitiveservices | models-dev | Input: $0.13 | Output: $0.50 | Provider: Azure Cognitive Services, Context: 32000, Output Limit: 4096 | |
| openrouter | openrouter | Input: $0.07 | Output: $0.35 | Phi-4-reasoning-plus is an enhanced 14B parameter model from Microsoft, fine-tuned from Phi-4 with additional reinforcement learning to boost accuracy on math, science, and code reasoning tasks. It uses the same dense decoder-only transformer architecture as Phi-4, but generates longer, more comprehensive outputs structured into a step-by-step reasoning trace and final answer. While it offers improved benchmark scores over Phi-4-reasoning across tasks like AIME, OmniMath, and HumanEvalPlus, its responses are typically ~50% longer, resulting in higher latency. Designed for English-only applications, it is well-suited for structured reasoning workflows where output quality takes priority over response speed. Context: 32768 |