Microsoft

Phi-3-mini instruct (4k)

Type
language model
Context
4K tokens
Max output
1K
Released
23 April 2024
API string
microsoft/phi-3-mini-4k-instruct
Weights
open

Prices by provider

Provider Input, $ per 1M Output, $ per 1M In our data since
Microsoft Foundry $0.13 $0.52 31 Jul 2026

Only the base tier and only per-token prices are shown. Batch, discounted and cached rates, as well as prices per image or per second of video, do not go into this table: they cannot stand in the same column as a price per million tokens.

The date in the last column is the day this price first entered our collection. The price may well be older: before that day we simply were not recording it. It has not changed since — otherwise a new row with a new date would stand in its place.

Measurement results

Task set Result Run conditions Measured by
Arena Score in English 1,117.38 1,109–1,125 — —
Arena Score, mathematics 1,111.44 1,099–1,124 — —
Arena Score, programming 1,093.1 1,081–1,105 — —
Arena Score in Spanish 1,084.05 1,052–1,117 — —
Arena Score in French 1,074.81 1,038–1,111 — —
Arena Score, overall 1,073.47 1,067–1,080 — —
Arena Score, hard prompts 1,072.48 1,063–1,082 — —
Arena Score, instruction following 1,053.74 1,045–1,062 — —
Arena Score, expert questions 1,044.91 1,026–1,064 — —
Arena Score, long queries 1,044.24 1,029–1,059 — —
Arena Score, creative writing 1,037.33 1,025–1,050 — —
Arena Score in Russian 1,021.26 1,008–1,034 — —
Arena Score, multi-turn dialogue 1,018.3 1,005–1,032 — —