# Phi 4 Multimodal

> Phi 4 Multimodal is an open-weight language model from Microsoft, released on 26 Feb 2025. It accepts text and generates text, with a 128K-token context window and up to 16K output tokens per response.

Source page: https://www.aimodel.directory/models/phi-4-multimodal-instruct
Last verified: 18 Nov 2026

## Specifications

- **Developer:** Microsoft
- **Release date:** 26 Feb 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nano-gpt/models/phi-4-multimodal-instruct.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nano-gpt/models/phi-4-multimodal-instruct.toml)
- **Weights:** Open weights (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nano-gpt/models/phi-4-multimodal-instruct.toml)
- **Context window:** 128K (128,000 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nano-gpt/models/phi-4-multimodal-instruct.toml)
- **Max output:** 16K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nano-gpt/models/phi-4-multimodal-instruct.toml)
- **Knowledge cutoff:** Jun 2024 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nano-gpt/models/phi-4-multimodal-instruct.toml)
- **Input:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nano-gpt/models/phi-4-multimodal-instruct.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nano-gpt/models/phi-4-multimodal-instruct.toml)
- **Reasoning mode:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nano-gpt/models/phi-4-multimodal-instruct.toml)
- **Tool calling:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nano-gpt/models/phi-4-multimodal-instruct.toml)
- **Structured output:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nano-gpt/models/phi-4-multimodal-instruct.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|

## FAQ

### What is the context window of Phi 4 Multimodal?

Phi 4 Multimodal has a context window of 128,000 tokens (128K) and can generate up to 16,384 tokens in a single response, according to models.dev.

### Is Phi 4 Multimodal open source?

Phi 4 Multimodal is an open-weight model. Check the license terms before commercial use.

### When was Phi 4 Multimodal released?

Microsoft released Phi 4 Multimodal on 26 Feb 2025, according to models.dev.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Phi 4 Multimodal", https://www.aimodel.directory/models/phi-4-multimodal-instruct