microsoft/phi-4 · Microsoft Azure AI
Microsoft's state-of-the-art 14B small language model (SLM) trained on synthetic reasoning datasets at $0.10/$0.30 per 1M tokens.
Last checked Aug 19, 2026. Calculations use the listed base rates; provider-specific tiers, cache writes, batch pricing, and long-context rules may differ. Confirm the current rate at the official provider source.
Input
$0.10
per 1M tokens
Output
$0.30
per 1M tokens
Cached input
—
not published
Context window
16.4K
max output 4.1K
Microsoft Phi-4 (14B) cost calculator
What Microsoft Phi-4 (14B) costs per task
| Use case | Input tokens | Output tokens | Cost / request | Monthly @ 1K req/day |
|---|---|---|---|---|
| Customer support chatbot | 3,500 | 350 | $0.000455 | $13.65 |
| RAG / search-augmented answers | 8,000 | 500 | $0.00095 | $28.50 |
| AI coding assistant | 12,000 | 2,000 | $0.0018 | $54.00 |
| Document summarization | 25,000 | 600 | $0.00268 | $80.40 |
| Agentic workflow | 40,000 | 1,500 | $0.00445 | $133.50 |
| Content generation | 800 | 1,200 | $0.00044 | $13.20 |
| Data extraction & tagging | 2,000 | 250 | $0.000275 | $8.25 |
| Translation | 5,000 | 5,500 | $0.00215 | $64.50 |
Assumes each use case's typical cacheable share of input. See full cost scenarios.
Compare with alternatives
| Model | Input /M | Output /M | Context | Chat request* |
|---|---|---|---|---|
| Microsoft Phi-4 (14B) | $0.10 | $0.30 | 16.4K | $0.00064 |
| GPT-5.6 Sol | $5.00 | $30.00 | 1.1M | $0.035 |
| GPT-5.6 Terra | $2.00 | $12.00 | 1.1M | $0.014 |
| GPT-5.6 Luna | $0.20 | $1.20 | 1.1M | $0.0014 |
| GPT-5.6 Cyber | $12.50 | $75.00 | 1.1M | $0.0875 |
| GPT-5.5 Standard | $5.00 | $30.00 | 512K | $0.035 |
| GPT-5.5 Pro | $30.00 | $180.00 | 512K | $0.21 |
| GPT-5.4 Workhorse | $2.50 | $15.00 | 256K | $0.0175 |
| GPT-5.4 mini | $0.75 | $4.50 | 256K | $0.00525 |
*4,000 in + 800 out tokens, 50% cached input where available.
Related calculations
FAQ
Microsoft Phi-4 (14B) costs $0.10 per 1M input tokens and $0.30 per 1M output tokens. Verified Aug 19, 2026 against https://azure.microsoft.com/en-us/pricing/details/cognitive-services/.
Microsoft Phi-4 (14B) supports a 16,384-token context window with up to 4,096 output tokens per request, tokenized with cl100k_base.
At $0.10/M input and $0.30/M output, Microsoft Phi-4 (14B) sits below GPT-5.6 Sol ($5.00/M in, $30.00/M out) — see the comparison table for full-workload differences.