Phi-4 Models by Microsoft Research
Last refreshed 2026-10-17. Next refresh: weekly.
Details
Capabilities
Links
WebsiteAbout
Phi-4 is Microsoft’s family of small language models (SLMs), spanning a 14B text model from Microsoft Research and later Phi-4-mini and Phi-4-multimodal variants. The line is aimed at memory- and latency-constrained settings, with an emphasis on reasoning- and STEM-focused training data. Phi-4-multimodal is a compact multimodal model that handles speech, vision, and text in one architecture; Phi-4-mini is a compact text model for instruction and tool-style workloads.
Decision facts
- Best fit
- reasoningvision and multimodal workstructured outputs
- Capability starting point
- Phi-4 14B with 16K context and structured outputs
- Lowest tracked input
- Phi-4 Mini · $0.050/1M · Novita AI
- Closest related family
- Azure Speech Services
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
Use when the workload needs reasoning, 128K context, and 3.8B parameters.
Use when the workload needs 15B parameters and multimodal inputs.
Use when the workload needs reasoning, 128K context, and 3.8B parameters.
Use when the workload needs multimodal, 128K context, and 5.6B parameters.
Use when the workload needs reasoning, 128K context, and 14B parameters.
Use when the workload needs reasoning, 128K context, and 14B parameters.
Use when the workload needs 16K context, 14B parameters, and structured outputs.
Use when the workload needs 128K context and 3.8B parameters.
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Phi-4 Mini Reasoning | Use when the workload needs reasoning, 128K context, and 3.8B parameters. | 2026-05 | reasoning128K context3.8B parameters | Current |
| Phi-4 Reasoning Vision 15B | Use when the workload needs 15B parameters and multimodal inputs. | 2026-03 | 15B parametersmultimodal inputs | Current |
| Phi-4 Mini Flash Reasoning | Use when the workload needs reasoning, 128K context, and 3.8B parameters. | 2025-12 | reasoning128K context3.8B parameters | Current |
| Phi 4 Multimodal Instruct | Use when the workload needs multimodal, 128K context, and 5.6B parameters. | 2025-02 | multimodal128K context5.6B parameters | Current |
| Phi 4 Reasoning | Use when the workload needs reasoning, 128K context, and 14B parameters. | 2025-01 | reasoning128K context14B parameters | Current |
| Phi 4 Reasoning Plus | Use when the workload needs reasoning, 128K context, and 14B parameters. | 2025-01 | reasoning128K context14B parameters | Current |
| Phi-4 14B | Use when the workload needs 16K context, 14B parameters, and structured outputs. | 2024-12 | 16K context14B parametersstructured outputs | Current |
| Phi-4 Mini | Use when the workload needs 128K context and 3.8B parameters. | 2024-12 | 128K context3.8B parameters | Current |
Release Timeline
6 release groupsSpecifications(8 models)
| Model | Released | Context | Parameters | Vision | Multimodal | Reasoning | Structured Outputs |
|---|---|---|---|---|---|---|---|
| Phi-4 Mini Reasoning | 2026-05 | 128K | 3.8B | No | No | Yes | No |
| Phi-4 Reasoning Vision 15B | 2026-03 | — | 15B | Yes | Yes | No | No |
| Phi-4 Mini Flash Reasoning | 2025-12 | 128K | 3.8B | No | No | Yes | No |
| Phi 4 Multimodal Instruct | 2025-02 | 128K | 5.6B | Yes | Yes | No | No |
| Phi 4 Reasoning | 2025-01 | 128K | 14B | No | No | Yes | No |
| Phi 4 Reasoning Plus | 2025-01 | 128K | 14B | No | No | Yes | No |
| Phi-4 14B | 2024-12 | 16K | 14B | No | No | No | Yes |
| Phi-4 Mini | 2024-12 | 128K | 3.8B | No | No | No | No |
Available From(6 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| Phi-4 Mini | Novita AI | $0.05 | $0.15 | Serverless |
| Phi-4 14B | OpenRouter | $0.07 | $0.14 | Serverless |
| Phi-4 14B | Featherless | $0.07 | $0.14 | Serverless |
| Phi 4 Reasoning Plus | Microsoft Foundry | $0.125 | $0.5 | Serverless |
| Phi 4 Reasoning Plus | Fireworks AI | $0.5 | $0.5 | Serverless |
| Phi 4 Reasoning | Fireworks AI | $0.5 | $0.5 | Serverless |
| Phi-4 14B | Fireworks AI | $0.9 | $0.9 | Serverless |
| Phi-4 Mini | Fireworks AI | $0.9 | $0.9 | Serverless |
| Phi 4 Multimodal Instruct | Fireworks AI | $0.9 | $0.9 | Serverless |
Popular comparisons in this family
- Phi-4 Mini Flash Reasoning vs Qwen3.5-9B106
- Together AI - Gemma 3n-e4B vs Phi-4 Mini Flash Reasoning98
- Gemma 2 9B SahabatAI Instruct vs Phi-4 Mini Flash Reasoning86
- ByteDance Doubao Seed 2.0 Pro vs Phi-4 Mini Flash Reasoning79
- Llama 3 8B Instruct vs Phi-4 Mini Flash Reasoning63
- Llama 3.2 1B Instruct vs Phi-4 Mini Flash Reasoning55
- Phi 3.5 Vision Instruct vs Phi-4 Mini Flash Reasoning53
- Grok 4.3 vs Phi-4 Reasoning Vision 15B53
- GPT-5 vs Phi-4 Mini Flash Reasoning51
- Hunyuan Hy3 Preview vs Phi-4 Reasoning Vision 15B50
Related Model Families
Models(8)
Phi-4 Mini Reasoning
Phi-4 Reasoning Vision 15B
Phi-4 Mini Flash Reasoning
Phi 4 Multimodal Instruct
Phi 4 Reasoning
Phi 4 Reasoning Plus
Phi-4 14B
Phi-4 Mini