Skip to content
Sovyron

Phi-4

phi128k context15k max outputreleased Dec 11, 2024Open weights

As of Nov 22, 2026, the cheapest Phi-4 API price is $0.056 per 1M input tokens (Kilo Gateway) and $0.112 per 1M output tokens (Kilo Gateway). Phi-4 is offered by 4 providers in the phi family, open weights.

Cheapest input
$0.056
Cheapest output
$0.112
Official
—
output per 1M tokens
Providers
4
offering this model
Spread
4.5×
max / min output
Free offers
0
free-tier offers

API pricing by provider

Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked.

Phi-4 API prices by provider in USD per 1M tokens, updated Nov 22, 2026
Kilo Gatewaymicrosoft/phi-4Cheapest$0.056Cheapest$0.112——16k37d ago
OpenRouteropenmicrosoft/phi-4$0.07$0.14——16k—
Azureopenphi-4$0.125$0.5——128k—
Azure Cognitive Servicesopenphi-4$0.125$0.5——128k—

Phi-4 price history

Output price per 1M tokens since tracking began on Sep 10, 2026, for the one provider whose rate moved. Each step is a recorded change. All recent price changes.

Phi-4 output price per 1M tokens by provider, Sep 10, 2026 to Nov 22, 2026$0$0.05$0.1$0.15$0.2Sep 10, 2026Oct 17, 2026Nov 22, 2026
Kilo Gateway$0.112
Phi-4 price changes by provider, newest first, USD per 1M tokens
DateProvider1M input1M outputChange
Kilo Gateway$0.07 → $0.056$0.14 → $0.112−20%

Phi-4 pricing FAQ

What is the cheapest Phi-4 API?

As of Nov 22, 2026, Kilo Gateway has the lowest Phi-4 output price at $0.112 per 1M tokens, and Kilo Gateway has the lowest input price at $0.056 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

How many providers offer Phi-4?

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

Is Phi-4 free?

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

What is the context window of Phi-4?

Phi-4 supports a 128k-token context window and up to 15k output tokens.

Token cost calculator

What a month costs at one provider's published rates. Enter the tokens you expect to send and receive; cached tokens use the cached-input price where the provider lists one, and count as ordinary input where it does not. See how much prompt caching saves and why output tokens cost more than input tokens.

Estimated

—