Phi API pricing

8 Microsoft models live through one API key and one balance, priced per million tokens.

Models live

$0.050/M

Lowest input price

128K

Largest context

Every Microsoft model below is callable right now through Rapid Router with one API key. The price next to each model is the provider's list price per million tokens; it is exactly what your balance is debited. Our platform fee is charged once, when you buy credits, so there is nothing added per request.

To use a Microsoft model, point the OpenAI SDK (or any OpenAI-compatible client) at https://rapidrouter.ai/api/v1, set the model string to the id shown in grey, and send the same request you send today.

Phi 3 Medium 4K Instructmicrosoft/phi-3-medium-4k-instruct

$0.140/M in$0.140/M out415ms100% ok

Phi 4microsoft/phi-4

Open-weight instruction model for adaptable chat and self-hosted production workloads

16K context$0.070/M in$0.140/M out460ms100% ok1y ago

Phi 4 Multimodalmicrosoft/phi-4-multimodal-instruct

Compact GPT model for low-latency assistance and high-volume workloads

128K context$0.050/M in$0.100/M out806ms100% ok1y ago

Phi 4 Multimodal (free)Freemicrosoft/phi-4-multimodal-instruct:free

Compact GPT model for low-latency assistance and high-volume workloads

128K contextFree/M inFree/M out754ms100% ok1y ago

Phi-4-reasoning-plusReasoningmicrosoft/phi-4-reasoning-plus