Phi 4
Microsoft · Open weights · Released Jan 10, 2025 · microsoft/phi-4
Best $0.07 in / $0.14 out via DeepInfra · bf16
16K contextStructured outputOpen weights
Available from 1 providerUSD / MTOK · PRICES 23 MINUTES AGO · SPEED 16 DAYS AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
| $0.07 | $0.14 | — | 16K | bf16 | 1.1s | 75 tok/s | 100.0% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 16 days ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
About
Microsoft Research 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
Context window16,384
Max output14,745
Modalities intext
Modalities outtext
LicenseOpen weights
ReleasedJan 10, 2025
Knowledge cutoff2024-06-30
TokenizerOther
WeightsHugging Face ↗
Embed badge
[](https://modelindex.ai/models/microsoft/phi-4)Sources
OpenRouter API23 minutes ago
AGGREGATORHugging Face23 minutes ago
COMMUNITYModelIndex benchmarks16 days ago
MEASUREDVerified 23 minutes ago · list prices, not negotiated rates.