Microsoft

Phi-3-small instruct (8k)

Type
language model
Context
8K tokens
Max output
2K
Released
23 April 2024
API string
microsoft/phi-3-small-8k-instruct
Weights
open

Prices by provider

Provider Input, $ per 1M Output, $ per 1M In our data since
Microsoft Foundry $0.15 $0.6 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 1,150.79 1,138–1,163 — —
Arena Score in English 1,150.7 1,143–1,159 — —
Arena Score in French 1,133.51 1,097–1,170 — —
Arena Score in Spanish 1,110.39 1,073–1,148 — —
Arena Score, overall 1,109.98 1,104–1,116 — —
Arena Score in Russian 1,109.56 1,096–1,123 — —
Arena Score, programming 1,101.9 1,090–1,113 — —
Arena Score, hard prompts 1,100.6 1,091–1,110 — —
Arena Score, long queries 1,087.89 1,075–1,101 — —
Arena Score, instruction following 1,087.09 1,078–1,096 — —
Arena Score, creative writing 1,083.2 1,070–1,096 — —
Arena Score, multi-turn dialogue 1,068.45 1,056–1,081 — —
Arena Score, expert questions 1,066.66 1,048–1,086 — —