Phi-4 Mini Instruct
AI model by Microsoft. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. Phi-4 Mini Instruct is a budget-tier option from Microsoft at $0.00/M output tokens. Despite the low price, it scores competitively on Intelligence Index (5.7) and Coding Index (3.8) — making it a candidate for high-volume production workloads where unit cost dominates.
Latency. On latency, Phi-4 Mini Instruct reports 45 tok/s output speed and 870ms time-to-first-token. Output speed is on the slower end; for real-time chat consider pairing with a streaming front-end or routing latency-sensitive requests to a faster model.
Cost model. For a workload of 1M input tokens + 100K output tokens, Phi-4 Mini Instruct costs $0.00 per million input-equivalent requests. Multiply by your monthly request volume to project the bill, and compare against the speed/correctness profile above to decide if the trade-off is worth it for your workload.
Editorial summary generated from public pricing and benchmark data (Artificial Analysis API). All numbers are sourced — see the Artificial Analysis methodology for benchmark definitions. Last refreshed 2026-09-06.
Compare with similar models
| Model | Input | Output | Speed |
|---|---|---|---|
Phi-4 Mini InstructCurrent | $0.00 | $0.00 | 45 tok/s |
| GLM-4.5V (Non-reasoning) | $0.60 | $1.80 | 70 tok/s |
| Gemini 3.5 Flash (high) | $1.50 | $9.00 | 205 tok/s |
| MiMo-V2.5-Pro | $0.43 | $0.87 | 35 tok/s |
| JT-35B-Flash | — | — | — |
| Mercury 2 | $0.25 | $0.75 | 804 tok/s |