Microsoft: Phi 4
by MicrosoftMicrosoft: Phi 4 is a large language model from Microsoft. It costs $0.070 per million input tokens and $0.140 per million output tokens. Its context window is 16K tokens.
- Input / 1M tokens
- $0.070
- Output / 1M tokens
- $0.140
- Cached input / 1M
- -
- Context window
- 16K
Not supported
tokens
Who serves it cheapest
1 hosts serve Phi 4. Same weights, same API - the price difference is pure margin and routing.
| Provider | Input / 1M | Output / 1M | Context | Throughput | Uptime 24h |
|---|---|---|---|---|---|
| DeepInfraCheapestbf16 | $0.070 | $0.140 | 16K | - | 100.0% |
About Phi 4
[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...
Specifications
| Model ID | microsoft/phi-4 |
|---|---|
| Provider | Microsoft |
| Context window | 16K tokens |
| Max output | 15K tokens |
| Input modalities | text |
| Output modalities | text |
| Knowledge cutoff | 2024-06-30 |
| Open weights | Yes - microsoft/phi-4 |
| Released | January 10, 2025 |
Cheaper alternatives
Models that cost less than Phi 4 while keeping at least half its context window and every input modality it supports.
Frequently asked
How much does Microsoft: Phi 4 cost?
$0.070 per million input tokens and $0.140 per million output tokens.
What is the context window of Microsoft: Phi 4?
16K tokens, with up to 15K tokens of output per request.
Confirm against the source: Microsoft official pricing.