Mistral Small vs GPT-4o mini

Side by side pricing and context for Mistral Small and GPT-4o mini. Rates are curated catalog values with last verified dates on each model page.

Mistral Small

Low-cost Mistral for classification and light chat. Useful high-volume default inside the Mistral family.

Input $0.060 / Output $0.180 per 1M

Context 128K · Approx

GPT-4o mini

Inexpensive OpenAI chat model for customer support and simple tools. Popular cheap baseline. Pair with Exact token counts when budgeting.

Input $0.150 / Output $0.600 per 1M

Context 128K · Exact (o200k_base)


Quick take

  • Mistral Small is cheaper on input in this catalog snapshot.
  • Mistral Small is cheaper on output in this catalog snapshot.
  • Both last verified on their model pages (2026-08-02 / 2026-08-02).

Rate table

MetricMistral SmallGPT-4o mini
Input / 1M$0.060$0.150
Output / 1M$0.180$0.600
Cached input / 1Mn/a$0.075
Context128K128K
TokenizerApproxExact (o200k_base)