All AI models · LLM benchmarks · Methodology

Mistral

Ministral 3 3B

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

Model facts

Context window
256K tokens
Maximum output
8K tokens
Cheapest paid input
$0.1 per 1M tokens
Cheapest paid output
$0.1 per 1M tokens
Open weights
yes
Providers
1

Capabilities and modalities

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

Artificial Analysis benchmarks

Compare this model on the full LLM benchmark leaderboard.

ConfigurationAAICodingMathOutput tokens/s
default7.14.822.0208.1

Observed price history

  • 2026-08-24: $0.1 input / $0.1 output per 1M tokens

API providers

  • Amazon Bedrock — model id mistral.ministral-3-3b-instruct; $0.1 input / $0.1 output per 1M tokens; provider documentation