Nvidia
Frontier

Mistral-Large-2 (NIM)

Enterprise

Mistral Large 2 served via NVIDIA NIM. Identical Mistral weights with NVIDIA enterprise integration.

Mistral-Large-2 (NIM) is a frontier AI model from Nvidia. It costs $2.00 per million input tokens and $6.00 per million output tokens (blended $3.20/M), with a 128,000-token context window.

RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.

INPUT
$2.00/M
per million input tokens
OUTPUT
$6.00/M
per million output tokens
BLENDED 70/30
$3.20/M
unchanged since 3 May
CONTEXT
128,000
tokens

Hand-maintained from Nvidia's published pricing; no check date on record.

What it is good at
  • Mistral Large 2 quality
  • NIM enterprise packaging
  • On-prem NVIDIA hosting
Typical use cases
  • NVIDIA-stack frontier inference
  • On-prem large-model deployments

Benchmarks

vs. best public score
Scores inherited from Mistral Large 2 — this is a hosted variant of the same open-weights model, so the underlying benchmark scores are identical.
MMLU84%
Multitask academic knowledge across 57 subjects. Source: Mistral AI (self-reported), MMLU, pretrained version, read 2026-11-10.
MATH70%
High-school competition math problems. Source: Mistral AI (self-reported), MATH (0-shot, no CoT), read 2026-11-10.
Python function synthesis from docstrings. Source: Mistral AI (self-reported), Human Eval, read 2026-11-10.
LMArena Elo1314 Elo
Crowd-sourced head-to-head preference Elo rating. Source: LMArena (independent), LMArena Text Arena score, read 2026-11-10.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources, treat as directional rather than authoritative.

More from Nvidia

See all 6 →

Frequently asked questions

How much does Mistral-Large-2 (NIM) cost?

Mistral-Large-2 (NIM) costs $2.00 per million input tokens and $6.00 per million output tokens, for a blended reference rate of $3.20 per million tokens.

What is Mistral-Large-2 (NIM)'s context window?

Mistral-Large-2 (NIM) supports up to 128,000 tokens of context in a single request.

What is Mistral-Large-2 (NIM) best for?

Mistral-Large-2 (NIM) is well suited to Mistral Large 2 quality, NIM enterprise packaging and On-prem NVIDIA hosting.

Who makes Mistral-Large-2 (NIM)?

Mistral-Large-2 (NIM) is developed and served by Nvidia.

Terms used on this page