All AI models · LLM benchmarks · Methodology

Mistral

Magistral Small 2506

Mistral reasoning model for transparent analysis, math, and complex decisions

Model facts

Context window
128K tokens
Maximum output
33K tokens
Cheapest paid input
$0.5 per 1M tokens
Cheapest paid output
$1.5 per 1M tokens
Open weights
no
Providers
2

Capabilities and modalities

tool calling, temperature control, text.

Observed price history

  • 2026-08-24: $0.5 input / $1.5 output per 1M tokens

API providers

  • Nvidia — model id mistralai/magistral-small-2506; free input / free output per 1M tokens; provider documentation
  • IO.NET — model id mistralai/Magistral-Small-2506; $0.5 input / $1.5 output per 1M tokens; provider documentation