token.app › Microsoft › Phi 4
Phi 4 pricing & benchmarks
Phi 4 is available from Microsoft at $0.070 per million input tokens and $0.140 per million output tokens ($0.088 blended at 3:1). It accepts up to 16,384 tokens of context. [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...
Pricing
Per million tokens · OpenRouter
Input$0.070
Output$0.140
Blended (3:1)$0.088
Specification
microsoft/phi-4
Context window16K
Max output16K
ReleasedJan 2025
LicenceOpen weights
Modalitiesin:text, out:text
Benchmarks
Independently run — not vendor self-reports. Every score links its source.
| Benchmark | Score | Config | Run | Source |
|---|---|---|---|---|
| GPQA Diamond | 56.1% ±2.6 | — | 2025-01-31 | Independently run · Epoch AI |
| OTIS Mock AIME | 13.8% ±3.7 | — | 2025-02-25 | Independently run · Epoch AI |
Scores published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0.
Cheaper models that score at least as well on GPQA Diamond
Strictly lower blended price AND an equal-or-higher GPQA Diamond score. One benchmark is one dimension — a model that wins here may still be weaker at your specific task.
| Model | Provider | Blended $/1M | GPQA Diamond | |
|---|---|---|---|---|
| gpt-oss-120b | OpenAI | $0.070 (−20%) | 75.8% | Compare → |
Compare Phi 4
FAQ
How much does Phi 4 cost?
Phi 4 costs $0.070 per million input tokens and $0.140 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $0.088 per million tokens.
What is Phi 4's context window?
Phi 4 accepts up to 16,384 tokens of context, and can generate up to 16,384 output tokens.
How good is Phi 4 on benchmarks?
Phi 4 scores 56.1% on GPQA Diamond, independently run and published by Epoch AI. 2 benchmark results are listed on this page, each with its run date and source.
Is there a cheaper model as good as Phi 4?
Yes — 1 model in our catalogue cost less per token than Phi 4 and score at least as high on the same benchmark. The cheapest is gpt-oss-120b at $0.070 per million tokens blended.