All AI models · LLM benchmarks · Methodology

Mistral

Mistral Medium 3.5 Thinking

Mistral model for multilingual chat, reasoning, and tool-assisted workflows

Model facts

Context window
256K tokens
Maximum output
33K tokens
Cheapest paid input
$1.5 per 1M tokens
Cheapest paid output
$7.5 per 1M tokens
Open weights
yes
Providers
1

Capabilities and modalities

reasoning, tool calling, structured output, attachments, open weights, text, image.

Observed price history

  • 2026-08-24: $1.5 input / $7.5 output per 1M tokens

API providers

  • NanoGPT — model id mistral/mistral-medium-3.5:thinking; $1.5 input / $7.5 output per 1M tokens; provider documentation