All AI models · LLM benchmarks · Methodology

Mistral

Mistral Medium 3.5

Balanced Mistral model for enterprise assistants, multilingual work, and tools

Model facts

Context window
262K tokens
Maximum output
262K tokens
Cheapest paid input
$0.75 per 1M tokens
Cheapest paid output
$3.75 per 1M tokens
Open weights
yes
Providers
15

Capabilities and modalities

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

Artificial Analysis benchmarks

Compare this model on the full LLM benchmark leaderboard.

ConfigurationAAICodingMathOutput tokens/s
default30.446.9not measured124.9

Observed price history

  • 2026-08-24: $1.67 input / $5.57 output per 1M tokens
  • 2026-08-26: $1.39 input / $7.13 output per 1M tokens
  • 2026-08-28: $0.75 input / $3.75 output per 1M tokens

API providers

  • Kenari (Free) — model id mistral-medium-3-5:free; free input / free output per 1M tokens; provider documentation
  • Nvidia — model id mistralai/mistral-medium-3.5-128b; free input / free output per 1M tokens; provider documentation
  • OpenRouter (batch) — model id mistralai/mistral-medium-3-5:batch; $0.75 input / $3.75 output per 1M tokens; provider documentation
  • Cortecs — model id mistral-medium-3.5; $1.39 input / $7.13 output per 1M tokens; provider documentation
  • evroc — model id mistralai/Mistral-Medium-3.5-128B; $1.73 input / $6.9 output per 1M tokens; provider documentation
  • Eden AI — model id mistral/mistral-medium-2604; $1.5 input / $7.5 output per 1M tokens; provider documentation
  • Kilo Gateway (Mistral) — model id mistralai/mistral-medium-3-5; $1.5 input / $7.5 output per 1M tokens; provider documentation
  • Mistral — model id mistral-medium-2604; $1.5 input / $7.5 output per 1M tokens; provider documentation
  • NanoGPT — model id mistral/mistral-medium-3.5; $1.5 input / $7.5 output per 1M tokens; provider documentation
  • OpenRouter — model id mistralai/mistral-medium-3-5; $1.5 input / $7.5 output per 1M tokens; provider documentation
  • Pioneer — model id mistral-medium-3.5; $1.5 input / $7.5 output per 1M tokens; provider documentation
  • Requesty — model id mistral-medium-3-5; $1.65 input / $8.25 output per 1M tokens; provider documentation
  • GreenPT — model id mistral-medium-3.5-128b; $2.05 input / $10.26 output per 1M tokens; provider documentation
  • Arena — model id mistral-medium-3.5; not published input / not published output per 1M tokens; provider documentation
  • SAP AI Core — model id mistralai--mistral-medium; not published input / not published output per 1M tokens; provider documentation