# Phi-4-mini API prices

Phi-4-mini (phi) — 128k context, 16k max output.
3 metered per-token offers from 3 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Azure | $0.075 | $0.3 | — | 128k |
| Azure Cognitive Services | $0.075 | $0.3 | — | 128k |
| NanoGPT | $0.17 | $0.68 | $0.085 | 128k |

## Summary

- Cheapest input: $0.075 per 1M tokens (Azure)
- Cheapest output: $0.3 per 1M tokens (Azure)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2024-12-11
- Inputs: text

## FAQ

### What is the cheapest Phi-4-mini API?

As of Oct 4, 2026, Azure has the lowest Phi-4-mini output price at $0.3 per 1M tokens, and Azure has the lowest input price at $0.075 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer Phi-4-mini?

3 providers list Phi-4-mini on Sovyron; 3 of them sell it at a metered per-token price.

### Is Phi-4-mini free?

No provider in the Sovyron catalog lists a free tier for Phi-4-mini.

### What is the context window of Phi-4-mini?

Phi-4-mini supports a 128k-token context window and up to 16k output tokens.

HTML page: https://sovyron.com/models/phi-4-mini/
Full dataset: https://sovyron.com/data/catalog.json