Phi-4-mini-flash-reasoning
transformerssafetensorsphi4flashtext-generationnlpmathcodeconversationalcustom_codeenarxiv:2507.06607license:mitregion:us
Context
131,072 tokens
Max Output
8,192 tokens
Released
6/19/2025
Providers
1
Overview
Phi-4-mini-flash-reasoning is a large language model developed by Microsoft. It supports 131,072 tokens context and is available through 1 API provider(s).
Key Highlights
- Unknown / Not disclosed
Brand
Microsoft
Organization
Country: USA
View all models, pricing and details from Microsoft.
Specifications
Basic Information
| Model | Phi-4-mini-flash-reasoning |
| Brand | Microsoft |
| Version | 4 |
| Model Type | transformers |
| Status | stable |
| Released | 6/19/2025 |
| Popularity | 15507 |
Architecture
| Parameter Size | 3.9B |
| Architecture Type | phi4flash |
| Attention Mechanism | Unknown / Not disclosed |
| Tokenizer | Unknown / Not disclosed |
| Vocabulary Size | Unknown / Not disclosed |
Context & I/O
| Context | 131,072 tokens |
| Max Output | 8,192 tokens |
| Modalities | Unknown / Not disclosed |
| Languages | en |
Capabilities
| Vision | No |
| Audio | No |
| Reasoning | No |
| Function Call | No |
| MCP | No |
| JSON Mode | No |
| Embedding | No |
Training Data
| Training Dataset | Unknown / Not disclosed |
| Estimated Data Size | Unknown / Not disclosed |
| Knowledge Cutoff | Unknown / Not disclosed |
Inference & Deployment
| API Access | Yes |
| VRAM Estimate | Unknown / Not disclosed |
| Quantization Support | Unknown / Not disclosed |
| Hardware Requirements | Unknown / Not disclosed |
Safety & Compliance
| Safety Evaluations | Unknown / Not disclosed |
| Content Policy | Unknown / Not disclosed |
| Region Restrictions | Unknown / Not disclosed |
License & Pricing
| License | mit |
| Commercial Use | Unknown / Not disclosed |
| Open Source | Yes |
Provider & Pricing
| Provider | Input | Output | Cache | Batch | Website |
|---|---|---|---|---|---|
| microsoft | $0.000/1M | $0.000/1M | - | - | Visit Website |
Price Changes
No recorded price changes.
Benchmarks
No benchmark data available.
Changelog
- Page created / data imported9/23/2026
- Last updated9/23/2026
Frequently Asked Questions
What is Phi-4-mini-flash-reasoning?
Phi-4-mini-flash-reasoning is a large language model developed by Microsoft.
Who developed Phi-4-mini-flash-reasoning?
Phi-4-mini-flash-reasoning was developed by Microsoft. You can learn more on the brand page or official website.
What is the context length of Phi-4-mini-flash-reasoning?
Phi-4-mini-flash-reasoning supports up to 131,072 tokens of context.
How much does Phi-4-mini-flash-reasoning API cost?
API pricing for Phi-4-mini-flash-reasoning starts at $0.000/1M per 1M input tokens and $0.000/1M per 1M output tokens. See the pricing table above for provider-specific rates.