<!-- https://models.searchit-agent.ai/en/models/phi-4/ | searchit Models -->

# Phi-4

Phi-4 by Microsoft: 1 offers. From €0.063 per 1M input tokens. No offer with EU processing is listed.

- [Calculate costs for this model](https://models.searchit-agent.ai/en/tools/cost-calculator/phi-4/)
- [Compare offers](https://models.searchit-agent.ai/ui-fat/modelle_api?q=phi-4)
- [View price history](https://models.searchit-agent.ai/ui-fat/modelle_api?q=phi-4)

## Profile

| Profile |  |
|---|---|
| Developer | Microsoft |
| Type | Language models |
| Origin | US |
| Input types | text |
| Context (tokens) | 16,384 |
| Max. output (tokens) | 14,745 |
| Reasoning | ohne |
| Parameters (bn) | 14.7 |
| Open weights | ✓ yes |
| Licence | MIT |
| VRAM at 4-bit (GB) | 13 (RTX PRO 4000) |
| Released | – |

[Open in the app](https://models.searchit-agent.ai/ui-fat/modelle_api?q=phi-4)

## Offers with processing in the EU (0)

No offers in this group.

[Open in the app](https://models.searchit-agent.ai/ui-fat/modelle_api?q=phi-4)

## Offers outside the EU (1)

| Provider | Country | Variant | Input | Output | Source | As of |
|---|---|---|---:|---:|---|---|
| [DeepInfra](https://models.searchit-agent.ai/en/providers/deepinfra/) | US | standard | €0.063 | €0.13 | [deepinfra.com](https://deepinfra.com/pricing) | 14 Oct 2026 |

_€ per 1M tokens. Source: providers' pricing pages, read and checked by searchit. As of 14 Oct 2026._

[Open in the app](https://models.searchit-agent.ai/ui-fat/modelle_api?q=phi-4)

## AI Act

Whether the developer has signed the Code of Practice for general-purpose AI models: unknown. What this means is explained under “EU and AI Act”. [EU processing and AI Act](https://models.searchit-agent.ai/en/knowledge/eu-and-ai-act/)

## Benchmarks

| Benchmarks |  |
|---|---:|
| GPQA Diamond (Artificial Analysis) | 57.5 |
| Humanity's Last Exam (Artificial Analysis) | 3.8 |
| Berkeley Function-Calling Leaderboard V4 | 28.8 |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 13.8 |
| Vectara HHEM-2.3 | 3.7 |
| Vectara HHEM-2.3 – antwortrate | 80.7 |
| Vectara HHEM-2.3 – halluzination | 3.7 |
| LLMStructBench: Benchmarking Large Language Model Structured Data Extraction (arXiv:2602.14743) | 0.66 |
| LLMStructBench: Benchmarking Large Language Model Structured Data Extraction (arXiv:2602.14743) – doc micro | 0.38 |
| LLMStructBench: Benchmarking Large Language Model Structured Data Extraction (arXiv:2602.14743) – f1 micro | 0.94 |
| LLMStructBench: Benchmarking Large Language Model Structured Data Extraction (arXiv:2602.14743) – score | 0.66 |
| MÖVE (Bundesdruckerei), arXiv 2606.13111 | 0.77 |
| MÖVE (Bundesdruckerei), arXiv 2606.13111 – qa | 0.69 |
| MÖVE (Bundesdruckerei), arXiv 2606.13111 – zusammenfassung | 0.77 |
| Structured Output Benchmark (SOB), arXiv 2604.25359 | 0.97 |
| Structured Output Benchmark (SOB), arXiv 2604.25359 – json pass | 0.97 |
| Structured Output Benchmark (SOB), arXiv 2604.25359 – wertgenauigkeit | 0.8 |
| MMLU-Pro (TIGER-Lab Leaderboard) | 70.4 |

_[Report an error on this page](https://models.searchit-agent.ai/en/report/report-error/?seite=https%3A%2F%2Fmodels.searchit-agent.ai%2Fen%2Fmodels%2Fphi-4%2F)_

---

Prices as of 14 Oct 2026. Providers' list prices, without guarantee.