All AI models · LLM benchmarks · Methodology

Ministral 3 3B Reasoning 2512

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

Model facts

Context window
262K tokens
Maximum output
262K tokens
Cheapest paid input
$1.04 per 1M tokens
Cheapest paid output
$0.548 per 1M tokens
Open weights
yes
Providers
1

Capabilities and modalities

reasoning, tool calling, attachments, temperature control, open weights, text, image.

Observed price history

  • 2026-08-24: $1.04 input / $0.548 output per 1M tokens

API providers

  • Clarifai — model id mistralai/completion/models/Ministral-3-3B-Reasoning-2512; $1.04 input / $0.548 output per 1M tokens; provider documentation