Microsoft: Phi 4
Microsoft Phi 4 is designed for handling text inputs within an extensive context length of 16,384 tokens and supports up to 16,384 output tokens. Currently, it does not offer tools support or reasoning capabilities; structured output is also not available. This model should be considered for those working with large volumes of text data where detailed reasoning and structured outputs are not required. With a blended benchmark score of 6.4 across one independent benchmark and pricing at $0.07 per million input tokens and $0.14 per million output tokens, it offers competitive value in its performance range.
Benchmark results
Independent, published benchmarks. Blended score 6.4 across 1 benchmark, last refreshed 2026-07-21. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| AI Index | broad capability composite | 8.0 |
- Model ID
- microsoft/phi-4
- Vendor
- microsoft
- Released
- January 2025
- Tokenizer
- Other
- Input Modalities
- text
- Output Modalities
- text
- Max Output
- 16,384 tokens
- Tool Calling
- not supported
- Structured Output
- ✓ supported
- Reasoning Mode
- not supported
- Vision
- text only
- Audio
- no
- Moderated
- no
What it costs in practice
Computed from the current $0.07/M input and $0.14/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | under $0.01 |
| Classify 1,000 customer emails | 500k in / 50k out | $0.04 |
| A month of a busy support chatbot | 5M in / 2M out | $0.63 |
Similar models
Quick answers
- How much does Microsoft: Phi 4 cost?
- $0.07 per million input tokens and $0.14 per million output tokens.
- What is Microsoft: Phi 4's context window?
- 16,384 tokens, roughly 24 pages of text in a single request.
- Does Microsoft: Phi 4 support tool calling?
- It supports structured output.
- Can Microsoft: Phi 4 process images?
- No, it is text-only on the input side.