Mistral AI

Mistral Large 2407

Type
language model
Context
131K tokens
Max output
33K
Released
19 November 2024
Knowledge cutoff
March 2024
API string
mistralai/mistral-large-2407
Weights
open

Prices by provider

Provider Input, $ per 1M Output, $ per 1M In our data since
Kilo Code $2 $6 31 Jul 2026
Microsoft Foundry $2 $6 31 Jul 2026
OpenRouter $2 $6 31 Jul 2026
Amazon Bedrock $3 $9 2 Aug 2026
Mistral AI $3 $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 1,289.16 1,284–1,294 — —
Arena Score, programming 1,277.11 1,269–1,285 — —
Arena Score in French 1,271.7 1,242–1,301 — —
Arena Score, overall 1,266.3 1,262–1,270 — —
Arena Score, mathematics 1,261.53 1,253–1,270 — —
Arena Score, long queries 1,257.74 1,249–1,266 — —
Arena Score, multi-turn dialogue 1,257.34 1,249–1,265 — —
Arena Score, hard prompts 1,256.78 1,250–1,263 — —
Arena Score in Russian 1,255.94 1,247–1,265 — —
Arena Score, instruction following 1,248.25 1,243–1,254 — —
Arena Score, creative writing 1,243.21 1,235–1,252 — —
Arena Score in Spanish 1,235.51 1,210–1,261 — —
Arena Score, expert questions 1,231.72 1,219–1,244 — —
Creative writing (Lech Mazur’s evaluation) 69 % — lechmazur/writing Github repository
MATH, difficulty level five 44.82 % · with a tuned harness Epoch evaluations
GPQA Diamond — graduate-level questions 32.03 % · with a tuned harness Epoch evaluations
Mock AIME 2024–2025 — olympiad problems 8.38 % · with a tuned harness Epoch evaluations
SimpleBench — trick questions 7 % — SimpleBench Leaderboard