tokenstat
tokenstat

Phi 4

azure-cognitive-services/phi-4 · rates as of · Benchmarks · Plans · Calculator

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

Cheapest input
$0.07
$/MTok · models.dev
Cheapest output
$0.14
$/MTok
Context
128K
tokens
Offers
9
3 sources

Offers

Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number. Free/$0 listings are hidden by default (1 omitted). Show free/$0 offers.

SourceProviderInputOutputCache readContext
models.devcheapestmicrosoft/phi-4Kilo Gateway$0.07$0.14$016K
OpenRoutermicrosoft/phi-4OpenRouter$0.07$0.14$016K
LiteLLMphi-4$0.07$0.14$0.007
LiteLLMmicrosoft/phi-4$0.07$0.14$0.007
LiteLLMdeepinfra/microsoft/phi-4$0.07$0.14$0.007
models.devphi-4Azure$0.125$0.5$0128K
models.devphi-4Azure$0.125$0.5$0128K
LiteLLMPhi-4$0.125$0.5$0.0125
LiteLLMazure_ai/Phi-4$0.125$0.5$0.0125

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Open weights
  • In: text
  • Out: text
Knowledge cutoff: 2023-10Released: 2024-12-11Family: phi

See what you actually spent

tokenstat prices your local sessions at list rates like these, with the cache split kept honest. Free, open source, runs on your machine.

$ curl -fsSL https://tokenstat.ai/install.sh | bash