Mistral AI

Mistral Large

Type
language model
Context
131K tokens
Max output
33K
Released
24 July 2024
API string
mistral-large-2411
Weights
open

Prices by provider

Provider Input, $ per 1M Output, $ per 1M In our data since
Google Vertex AI $2 $6 31 Jul 2026
Helicone $2 $6 31 Jul 2026
Kilo Code $2 $6 31 Jul 2026
Merge Gateway $2 $6 31 Jul 2026
Mistral AI $2 $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 in French 1,324.21 1,283–1,365 — —
Arena Score in English 1,283.92 1,279–1,289 — —
Arena Score, programming 1,275.94 1,267–1,285 — —
Arena Score in Spanish 1,265.51 1,220–1,311 — —
Arena Score, overall 1,265.45 1,261–1,270 — —
Arena Score, long queries 1,261.71 1,252–1,271 — —
Arena Score, mathematics 1,261.09 1,252–1,270 — —
Arena Score, multi-turn dialogue 1,259.59 1,251–1,269 — —
Arena Score, hard prompts 1,256.97 1,250–1,264 — —
Arena Score in Russian 1,250.66 1,241–1,261 — —
Arena Score, instruction following 1,249.26 1,243–1,255 — —
Arena Score, creative writing 1,242.26 1,233–1,251 — —
Arena Score, expert questions 1,207.5 1,193–1,222 — —
MATH, difficulty level five 50.28 % · with a tuned harness Epoch evaluations
GPQA Diamond — graduate-level questions 35.1 % · with a tuned harness Epoch evaluations
Mock AIME 2024–2025 — olympiad problems 7.69 % · with a tuned harness Epoch evaluations