NVIDIAActive

Phi 4 Multimodal

General-purpose chat model for instruction following, writing, and analysis

JSONEmbed chartCompare
Context
128,000
Max output
16,384
Input / 1M
$0.07
Output / 1M
$0.11
Providers
2
01Profile

Profile

Released
2025-07-26
Last updated
2025-07-26
Knowledge cutoff
Weights
Closed
02Capabilities

Capabilities

Input
text
Output
text
Reasoning
No
Tool calling
No
Structured output
No
Attachments
No
Cache read
Cache write
03Pricing

Pricing across 1 providers

Per 1M tokens, USD. Sorted by input price. First-party row highlighted.

ProviderProvider model idInputOutputCache readContext
nvidiafirst-partymicrosoft/phi-4-multimodal-instructNot listedNot listedNot listed128,000
nano-gptphi-4-multimodal-instruct$0.07$0.11$0.04128,000
04History

Change history

10+ recent events since 2025-07-26

2026-08-03Removedgithub-modelsofferingremoved→ new
2026-06-24Removedevrocofferingremoved→ new
2026-05-03Addednvidiaoffering→ new
2026-02-18Addedevrocoffering→ new
2026-02-17Addednano-gptoffering→ new
2025-09-23Removednvidiaofferingremoved→ new
2025-09-05Addednvidiaoffering→ new
2025-08-04Price upgithub-modelsinput / 1M→ Not listed
2025-08-04Price upgithub-modelsoutput / 1M→ Not listed
2025-06-27Addedgithub-modelsoffering→ new
as of 2026-09-16
About ·Corrections ·Contact ·Privacy ·EN / 中文 / 繁體
HomeModelsLabsProvidersToolsRankingsChangesNews