Microsoft Phi-4 (14B) charges $0.10 per 1M input tokens and $0.30 per 1M output tokens. Real bills depend on your input/output split — the tables below price Microsoft Phi-4 (14B) at 1K–1M tokens across common workload shapes. Verified Aug 19, 2026
Cost by token volume
| Volume | Input-heavy (90/10) | Balanced (70/30) | Output-heavy (30/70) | All input | All output |
|---|---|---|---|---|---|
| 1,000 tokens | $0.00012 | $0.00016 | $0.00024 | $0.0001 | $0.0003 |
| 10,000 tokens | $0.0012 | $0.0016 | $0.0024 | $0.001 | $0.003 |
| 100,000 tokens | $0.012 | $0.016 | $0.024 | $0.01 | $0.03 |
| 1 million tokens | $0.12 | $0.16 | $0.24 | $0.10 | $0.30 |
Uncached. Volume links open interactive pages with adjustable splits.
Monthly projections
| Scale | Requests / day | Chat workload / month | Agentic workload / month* |
|---|---|---|---|
| 100 req/day | 3,000 | $1.92 | $13.35 |
| 1K req/day | 30,000 | $19.20 | $133.50 |
| 10K req/day | 300,000 | $192.00 | $1,335.00 |
| 100K req/day | 3,000,000 | $1,920.00 | $13,350.00 |
Chat: 4K in / 800 out, 50% cached. *Agentic: 40K in / 1.5K out, 65% cached. Model your exact mix in the monthly cost calculator.
FAQ
1M purely input tokens cost $0.10; 1M purely output tokens cost $0.30. A typical mixed workload lands in between — see the volume table for exact splits.
A chat-style request (4,000 input + 800 output) costs about $0.00064 with 50% cached input, or $0.00064 without caching.
At 1,000 requests/day of a chat workload (4K in / 800 out, 50% cached): $19.20/month. At 10,000 requests/day: $192.00/month. Model your exact mix with the monthly cost calculator.