All AI models · LLM benchmarks · Methodology

Mistral

Devstral 2

Mistral's coding-agent model for repository work, terminal tasks, and software fixes

Model facts

Context window
262K tokens
Maximum output
262K tokens
Cheapest paid input
$0.4 per 1M tokens
Cheapest paid output
$2 per 1M tokens
Open weights
yes
Providers
18

Capabilities and modalities

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

Artificial Analysis benchmarks

Compare this model on the full LLM benchmark leaderboard.

ConfigurationAAICodingMathOutput tokens/s
default19.231.336.7126.1

Observed price history

  • 2026-08-24: $0.4 input / $2 output per 1M tokens

API providers

  • DevPass (LLM Gateway) — model id devstral-2512; $0.4 input / $2 output per 1M tokens; provider documentation
  • Eden AI — model id mistral/devstral-2512; $0.4 input / $2 output per 1M tokens; provider documentation
  • Eden AI (latest) — model id mistral/devstral-medium-latest; $0.4 input / $2 output per 1M tokens; provider documentation
  • Kilo Gateway — model id mistralai/devstral-2512; $0.4 input / $2 output per 1M tokens; provider documentation
  • LLM Gateway (Mistral AI) — model id mistral/devstral-2512; $0.4 input / $2 output per 1M tokens; provider documentation
  • Merge Gateway — model id mistral/devstral-2512; $0.4 input / $2 output per 1M tokens; provider documentation
  • Merge Gateway (latest) — model id mistral/devstral-medium-latest; $0.4 input / $2 output per 1M tokens; provider documentation
  • Mistral — model id devstral-2512; $0.4 input / $2 output per 1M tokens; provider documentation
  • Mistral — model id devstral-latest; $0.4 input / $2 output per 1M tokens; provider documentation
  • Mistral (latest) — model id devstral-medium-latest; $0.4 input / $2 output per 1M tokens; provider documentation
  • OpenRouter — model id mistralai/devstral-2512; $0.4 input / $2 output per 1M tokens; provider documentation
  • Opper — model id mistral/devstral-2512; $0.4 input / $2 output per 1M tokens; provider documentation
  • Pioneer — model id devstral-2; $0.4 input / $2 output per 1M tokens; provider documentation
  • Vercel AI Gateway — model id mistral/devstral-2; $0.4 input / $2 output per 1M tokens; provider documentation
  • Cortecs — model id devstral-2512; $0.478 input / $2.39 output per 1M tokens; provider documentation
  • GreenPT — model id devstral-2-123b-instruct-2512; $0.57 input / $2.74 output per 1M tokens; provider documentation
  • AnyAPI — model id mistralai/devstral-2512; not published input / not published output per 1M tokens; provider documentation
  • Arena — model id devstral-2; not published input / not published output per 1M tokens; provider documentation