Phi 4

Microsoft · microsoft/phi-4

← Back to leaderboard

[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...

Phi 4 ranks #71 of 348 models in the default AI Benchmark Hub order (quality first, then cost). At $0.11 blended per million tokens, it is cheaper than 91% of models with published API pricing. Its 16,384-token context window is 16.0× smaller than the catalog median (262,144 tokens).

open weightstexttext->text

Context

Max context: 16384
Max output: 14745

Pricing

Input / 1M: 0.07
Output / 1M: 0.14
Blend / 1M: 0.11

Quality

Quality index:

Provider

Provider: Microsoft
Moderated: no

Monthly cost at this blended rate

Estimated API spend if every token is billed at $0.11per million (the blend of this model's input and output prices). Real bills depend on the input/output mix.

Tokens / monthEst. cost (USD)
1,000,000$0.11
10,000,000$1.05
100,000,000$10.50

Related models

Same lab, similar price, or similar quality — useful next comparisons.

More from Microsoft

Closest API price