All AI models · LLM benchmarks · Methodology

Mistral

Devstral Small 2505

Mistral coding agent model for repository tasks and software engineering workflows

Model facts

Context window
128K tokens
Maximum output
128K tokens
Cheapest paid input
$0.06 per 1M tokens
Cheapest paid output
$0.06 per 1M tokens
Open weights
yes
Providers
3

Capabilities and modalities

tool calling, temperature control, open weights, text.

Observed price history

  • 2026-08-24: $0.06 input / $0.06 output per 1M tokens

API providers

  • NanoGPT (Mistral) — model id mistralai/Devstral-Small-2505; $0.06 input / $0.06 output per 1M tokens; provider documentation
  • IO.NET — model id mistralai/Devstral-Small-2505; $0.05 input / $0.22 output per 1M tokens; provider documentation
  • Mistral — model id devstral-small-2505; $0.1 input / $0.3 output per 1M tokens; provider documentation