All AI models · LLM benchmarks · Methodology

Mistral

Ministral 3 14B

Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads

Model facts

Context window
262K tokens
Maximum output
128K tokens
Cheapest paid input
$0.2 per 1M tokens
Cheapest paid output
$0.2 per 1M tokens
Open weights
yes
Providers
3

Capabilities and modalities

tool calling, structured output, attachments, temperature control, open weights, text, image.

Artificial Analysis benchmarks

Compare this model on the full LLM benchmark leaderboard.

ConfigurationAAICodingMathOutput tokens/s
default11.214.430.097.0

Observed price history

  • 2026-08-24: $0.2 input / $0.2 output per 1M tokens

API providers

  • DigitalOcean — model id mistral-3-14B; $0.2 input / $0.2 output per 1M tokens; provider documentation
  • NanoGPT — model id mistralai/ministral-14b-instruct-2512; $0.1 input / $0.4 output per 1M tokens; provider documentation
  • Infomaniak — model id mistralai/Ministral-3-14B-Instruct-2512; $0.37 input / $0.5 output per 1M tokens; provider documentation