Microsoft

Phi-3-medium instruct (4k)

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

Prices by provider

Provider Input, $ per 1M Output, $ per 1M In our data since
Microsoft Foundry $0.17 $0.68 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, mathematics 1,173.44 1,163–1,184 — —
Arena Score in English 1,169.42 1,163–1,176 — —
Arena Score in Russian 1,144.02 1,133–1,155 — —
Arena Score, overall 1,137.71 1,133–1,143 — —
Arena Score, programming 1,130.61 1,120–1,141 — —
Arena Score, hard prompts 1,126.87 1,119–1,135 — —
Arena Score, long queries 1,120.35 1,107–1,133 — —
Arena Score, instruction following 1,113.9 1,107–1,121 — —
Arena Score in French 1,109.19 1,075–1,143 — —
Arena Score, expert questions 1,107.69 1,090–1,126 — —
Arena Score, creative writing 1,106.87 1,096–1,118 — —
Arena Score in Spanish 1,094.33 1,063–1,125 — —
Arena Score, multi-turn dialogue 1,088.03 1,077–1,099 — —