All AI models · LLM benchmarks · Methodology

Mistral

Ministral 3 8B

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

Model facts

Context window
262K tokens
Maximum output
262K tokens
Cheapest paid input
$0.15 per 1M tokens
Cheapest paid output
$0.15 per 1M tokens
Open weights
yes
Providers
2

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
default9.09.731.7113.5

Observed price history

  • 2026-08-24: $0.15 input / $0.15 output per 1M tokens

API providers

  • Amazon Bedrock — model id mistral.ministral-3-8b-instruct; $0.15 input / $0.15 output per 1M tokens; provider documentation
  • DigitalOcean — model id ministral-3-8b-instruct-2512; not published input / not published output per 1M tokens; provider documentation