Phi-4-mini

by MicrosoftChatunverified match

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

Context
128K tokens
Max output
4,096 tokens
Parameters
3.8B (total or active not stated)
Released
2024-12-11
Weights
Open

microsoft/phi-4-mini

Specifications

Full facts as recorded, incl. what is unknown.

Released
2024-12-11
Weights
Open
Input
Text
Output
Text
Context window
128,000 max across endpoints
Max output
4,096
Providers
2
Epoch Capabilities Index
not evaluated
Direct price range
$0.075 in · $0.30 out per 1M tokens · across all 2 providers
More details
Last updated
2024-12-11
Knowledge cutoff
2023-10
Parameters
3.8B (total or active not stated)
Developer country
United States of America
Training compute
10.0×10²² FLOP

Capabilities

Across all endpoints: supported if any endpoint supports it.

  • Tool calling
  • Parallel toolsunknown
  • Structured outputunknown
  • Reasoning
  • Image input
  • PDF input
  • Audio input
  • Audio outputunknown
  • Video input
  • Prompt cachingunknown
  • Web searchunknown
  • Computer useunknown
  • System messagesunknown
  • Assistant prefillunknown
  • Temperature
  • Streamingunknown
  • Attachments

Endpoints

One row per provider and variant; gateways are listed separately.

Loading endpoints…

Price history

No change since 19 Oct 2026. The cheapest direct price has been $0.075 in / $0.30 out per 1M tokens at Azure on every data refresh since then.

Tracked from 19 Oct 2026. Headline-eligible direct prices only, so a price the sanity check flags never draws a spike. Series as JSON

Cost calculator

Loading endpoints…

More from Microsoft

Newest Microsoft models in the catalogue. All Microsoft models

ModelReleasedContextListed price
Microsoft-Decision-12026-10-0932.8Kunpriced
MAI-Voice-2.12026-10-01—unpriced
MAI-Voice-2.1-Flash2026-10-01—unpriced
MAI-Transcribe-2-Streaming2026-10-01—unpriced
MAI-Image-2.62026-09-044.1Kunpriced
MAI-Image-2.6-Flash2026-09-044.1Kunpriced
MAI-Transcribe 22026-09-03—unpriced
MAI-Code-1.1-Flash2026-08-11256K$0.20 via GitHub Copilot
Heads up: prices are indicative list rates scraped from provider pricing pages; verify with the provider before relying on them. Report incorrect data for this model