tokenstat
tokenstat
Nano Gpt

Phi 4 Multimodal

nano-gpt/phi-4-multimodal-instruct · rates as of · Benchmarks · Plans · Calculator

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

Cheapest input
$0
$/MTok · models.dev
Cheapest output
$0
$/MTok
Context
128K
tokens
Offers
5
2 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. Showing free/$0 offers. Hide them.

SourceProviderInputOutputCache readContext
models.devcheapestmicrosoft/phi-4-multimodal-instructGitHub Models$0$0$0128K
models.devmicrosoft/phi-4-multimodal-instructNVIDIA$0$0$0128K
models.devphi-4-multimodal-instructNanoGPT$0.07$0.11$0128K
LiteLLMPhi-4-multimodal-instruct$0.08$0.32$0.008
LiteLLMazure_ai/Phi-4-multimodal-instruct$0.08$0.32$0.008

Capabilities

  • Reasoning
  • Tool calling
  • Open weights
  • In: text
  • In: image
  • In: audio
  • Out: text
Knowledge cutoff: 2023-10Released: 2025-07-26Family: 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