Mistral AI

Ministral 8B (latest)

Type
language model
Context
128K tokens
Max output
128K
Released
1 October 2024
API string
mistral/ministral-8b
Weights
open

Prices by provider

Provider Input, $ per 1M Output, $ per 1M In our data since
vercel_ai_gateway $0.1 $0.1 31 Jul 2026
Vercel $0.1 $0.1 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 1,212.6 1,201–1,224 — —
Arena Score, long queries 1,212.19 1,192–1,232 — —
Arena Score, programming 1,202.38 1,184–1,221 — —
Arena Score in Russian 1,194.25 1,175–1,214 — —
Arena Score, hard prompts 1,191.5 1,176–1,207 — —
Arena Score, overall 1,191.07 1,182–1,200 — —
Arena Score, mathematics 1,188.26 1,169–1,208 — —
Arena Score, creative writing 1,175.12 1,154–1,197 — —
Arena Score, expert questions 1,169.36 1,140–1,199 — —
Arena Score, multi-turn dialogue 1,166.38 1,148–1,185 — —
Arena Score, instruction following 1,161.05 1,148–1,174 — —