Phi 4 pricing
[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 parameters, it was trained on a mix of high-quality synthetic datasets, data from curated websites, and academic materials. It has undergone careful improvement to follow instructions accurately and maintain strong safety standards. It works best with English language inputs. For more info. Below you will find 3 current rows with input and output dollars per million. Right now the lowest input is $0.065 and the lowest output is $0.140.
Pricing across providers
Every row is a seller of Phi 4 with token pricing we track. The cheapest input in this snapshot is from Openrouter. The bar chart shows the same input and output dollars per million for a quick scan.
| Provider | Input / 1M | Output / 1M | Cached input | Batch |
|---|---|---|---|---|
O Openrouter | $0.065 | $0.140 | — | — |
A Azure | $0.125 | $0.500 | — | — |
D DeepInfra | $0.070 | $0.140 | — | — |
Input vs output · per provider
Cost calculator
Pick any of the providers above and type how many tokens you expect per day, week, or year. We turn that into rough dollar totals for Phi 4.
Provider
0.006500¢ / req
0.007000¢ / req
Model specifications
These fields describe Phi 4 as we store it (source: Microsoft). They sit next to price so buyers can check limits and tools in one place.
- Context window
- 16,384 tokens
- Max output
- 16,384 tokens
- Vision (images)
- No
- Tool / function calling
- Yes
- Streaming
- No
- Released
- Jan 2025
- Primary provider
- Microsoft
- Model family
- N/A
Compare Phi 4
Open a pair page to see Phi 4 next to another model with a shared provider matrix. 6 shortcuts below.
Frequently asked questions
Quick frequently asked items for Phi 4 pricing and limits. The short model note from our index: [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 parameters,...
Also from Microsoft
Other models by Microsoft with live pricing in our catalog.