128K tokens
Context window
Mistral AI Mistral
Mistral Large
Fast extraction and classification
32K tokens
Max output
$2
Input per 1M
$6
Output per 1M
2024
Knowledge cutoff
text
Modalities
Last verified 20 May 2026 Report a correction
What it tends to refuse
Standard safety categories, comparatively permissive on security research
Rewards tight prompts. A short role line, the rules, the input. Long rambling context hurts rather than helps.
Standing rules for this model go in Modelfile, not in every message.
See the config files.
Written for Mistral
All 3Ollama
The simplest way to get a local model answering on your own machine. One command to install, one to pull a model, and an API on localhost that most…
Tested on Llama 3.3 70B · May 2026
- GuideLlamaMistral
Running a model on your own machine
What local models are genuinely good for, what hardware you need, and what to change in prompts that came from a hosted model.
- ConfigLlamaMistral
Ollama Modelfile for a local code assistant
A Modelfile with a system prompt and parameters tuned for short, correct code answers on a local model.