Phi 4
microsoft/phi-4
Compare with WizardLM-2 8x22B, GLM 5.2, DeepSeek V4 Flash 0731
ComparePhi 4
| State | ||||||||
|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 100% | 379ms | 4.45s | 70 tps | 16K | $0.070 / $0.140 |
- DeepInfra100%Healthy24h 100%
- p50
- 379ms
- p99
- 4.45s
- Throughput
- 70 tps
- Context
- 16K
- $/Mtok
- $0.070 / $0.140
deepinfra/bf16bf16
Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
Availability
Axis starts at 90% so small differences stay visible; it expands to 0 when an endpoint falls below.
Time to first token
Logarithmic axis — the fleet spans two orders of magnitude. P50 is OpenRouter's rolling 30-minute window.
Throughput
Median tokens per second.