Microsoft
Phi 4 Multimodal
Multimodal model for analyzing text, images, documents, and rich media
Model facts
- Context window
- 128K tokens
- Maximum output
- 16K tokens
- Cheapest paid input
- $0.07 per 1M tokens
- Cheapest paid output
- $0.11 per 1M tokens
- Open weights
- yes
- Providers
- 4
Capabilities and modalities
attachments, temperature control, open weights, text, image, audio.
Artificial Analysis benchmarks
Compare this model on the full LLM benchmark leaderboard.
| Configuration | AAI | Coding | Math | Output tokens/s |
|---|---|---|---|---|
| default | 4.2 | not measured | not measured | 24.5 |
Observed price history
- 2026-08-24: $0.07 input / $0.11 output per 1M tokens
API providers
- Nvidia — model id microsoft/phi-4-multimodal-instruct; free input / free output per 1M tokens; provider documentation
- NanoGPT — model id phi-4-multimodal-instruct; $0.07 input / $0.11 output per 1M tokens; provider documentation
- Azure — model id phi-4-multimodal; $0.08 input / $0.32 output per 1M tokens; provider documentation
- Azure Cognitive Services — model id phi-4-multimodal; $0.08 input / $0.32 output per 1M tokens; provider documentation