NVIDIAphi familyActive

Phi-4-Mini

Efficient model for low-latency assistance, extraction, and routine automation

JSONEmbed chartCompare
Context
131,072
Max output
16,384
Input / 1M
$0.17
Output / 1M
$0.68
Providers
2
01Profile

Profile

Released
2024-12-01
Last updated
2025-09-05
Knowledge cutoff
2024-12
Weights
Open
02Capabilities

Capabilities

Input
text
Output
text
Reasoning
No
Tool calling
Yes
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-mini-instructNot listedNot listedNot listed131,072
nano-gptphi-4-mini-instruct$0.17$0.68$0.09128,000
04History

Change history

12+ recent events since 2024-12-01

2026-08-04Removedwandbofferingremoved→ new
2026-08-03Removedgithub-modelsofferingremoved→ new
2026-08-02Removedkiloofferingremoved→ new
2026-07-08DeprecatedwandbStatus→ deprecated
2026-06-30Removedopenrouterofferingremoved→ new
2026-05-15Addedopenrouteroffering→ new
2026-05-07Addedkilooffering→ new
2026-03-12ContextwandbMax output4,096→ 128,000
2026-02-17Addednano-gptoffering→ new
2025-09-23Addednvidiaoffering→ new
2025-08-04Price upgithub-modelsinput / 1M→ Not listed
2025-08-04Price upgithub-modelsoutput / 1M→ Not listed
as of 2026-09-16
About ·Corrections ·Contact ·Privacy ·EN / 中文 / 繁體
HomeModelsLabsProvidersToolsRankingsChangesNews