All AI models · LLM benchmarks · Methodology

Mistral

Codestral 2508

Mistral coding model for code completion, generation, and developer workflows

Model facts

Context window
256K tokens
Maximum output
205K tokens
Cheapest paid input
$0.3 per 1M tokens
Cheapest paid output
$0.9 per 1M tokens
Open weights
yes
Providers
4

Capabilities and modalities

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

Observed price history

  • 2026-08-24: $0.3 input / $0.9 output per 1M tokens

API providers

  • Kilo Gateway (Mistral) — model id mistralai/codestral-2508; $0.3 input / $0.9 output per 1M tokens; provider documentation
  • NanoGPT — model id mistralai/codestral-2508; $0.3 input / $0.9 output per 1M tokens; provider documentation
  • OpenRouter — model id mistralai/codestral-2508; $0.3 input / $0.9 output per 1M tokens; provider documentation
  • Cortecs — model id codestral-2508; $0.334 input / $1 output per 1M tokens; provider documentation