Mistral AI

Mistral: Mistral Small 3

Type
language model
Context
33K tokens
Max output
16K
Released
29 December 2025
Knowledge cutoff
October 2023
API string
mistralai/mistral-small-24b-instruct-2501
Weights
open

Prices by provider

Provider Input, $ per 1M Output, $ per 1M In our data since
DeepInfra $0.05 $0.08 31 Jul 2026
Kilo Code $0.05 $0.08 31 Jul 2026
OpenRouter $0.05 $0.08 31 Jul 2026
Fireworks AI $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 1,256.01 1,249–1,263 — —
Arena Score, programming 1,246.22 1,234–1,259 — —
Arena Score, long queries 1,246.04 1,233–1,260 — —
Arena Score, mathematics 1,240.12 1,227–1,253 — —
Arena Score, overall 1,233.68 1,228–1,240 — —
Arena Score, hard prompts 1,233.26 1,224–1,243 — —
Arena Score, multi-turn dialogue 1,216.58 1,204–1,229 — —
Arena Score in Russian 1,215.2 1,201–1,230 — —
Arena Score, instruction following 1,214.45 1,206–1,223 — —
Arena Score in French 1,202.88 1,153–1,252 — —
Arena Score, expert questions 1,201.38 1,181–1,222 — —
Arena Score, creative writing 1,195.12 1,183–1,207 — —