Mistral AI

Mixtral 8x22B

Type
language model
Context
66K tokens
Max output
33K
Released
11 December 2025
API string
mistralai/mixtral-8x22b-instruct-v0.1

Prices by provider

Provider Input, $ per 1M Output, $ per 1M In our data since
Nscale $0.6 $0.6 31 Jul 2026
anyscale $0.9 $0.9 31 Jul 2026
NanoGPT $0.9 $0.9 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 1,187.29 1,182–1,193
Arena Score, mathematics 1,184.32 1,175–1,193
Arena Score, programming 1,166.08 1,158–1,175
Arena Score in French 1,164.77 1,139–1,191
Arena Score, overall 1,162.15 1,158–1,167
Arena Score in Russian 1,156.81 1,147–1,167
Arena Score, hard prompts 1,150.02 1,143–1,157
Arena Score in Spanish 1,149.92 1,124–1,175
Arena Score, instruction following 1,147.6 1,141–1,154
Arena Score, long queries 1,143.99 1,134–1,154
Arena Score, creative writing 1,141.76 1,132–1,151
Arena Score, multi-turn dialogue 1,130.21 1,121–1,139
Arena Score, expert questions 1,112.73 1,099–1,126
Cybench — cybersecurity tasks 7.5 % · with a tuned harness Cybench leaderboard
WeirdML — unusual machine learning tasks 3.17 % WeirdML Leaderboard