128K tokens
Context window
Mistral AI Mistral
Mistral Large
Fast extraction and classification
32K tokens
Max output
Paid
Cost
2024
Knowledge cutoff
text
Modalities
Last verified 20 May 2026 Pricing is deliberately not listed here - check the vendor's own page. Report a correction
What it tends to refuse
Standard safety categories, fairly relaxed on security research
Tight prompts work best: a one-line role, the rules, the input. Pile on background and the answers get worse.
Standing rules for this model go in Modelfile, not in every message.
See the config files.
Written for Mistral
All 3Ollama
The easiest way to get a local model answering on your own machine. One command installs it, one pulls a model, and an API appears on localhost that…
Tested on Llama 3.3 70B · May 2026
- 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.
- 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.