Is Mistral Small 4 119B or Llama 3.1 8B Instruct cheaper?

Llama 3.1 8B Instruct is cheaper on output tokens ($0.25 vs $3.00 per 1M).

Which has the larger context window, Mistral Small 4 119B or Llama 3.1 8B Instruct?

Mistral Small 4 119B has the larger context window (256K tokens).

Mistral Small 4 119B vs Llama 3.1 8B Instruct

Llama 3.1 8B Instruct is cheaper on output tokens, while Mistral Small 4 119B offers a larger context window. Choose Mistral Small 4 119B or Llama 3.1 8B Instruct based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Mistral Small 4 119B	Llama 3.1 8B Instruct
Provider	Regolo AI	Regolo AI
Input / 1M tokens	$0.75	$0.05
Output / 1M tokens	$3.00	$0.25
Context window	256K	120K
Parameters	—	—
Open weights	No	No
Released	Mar 2026	Apr 2025

Mistral Small 4 119B details →Llama 3.1 8B Instruct details →

FAQ

Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.