Which has the larger context window, Mistral: Mixtral 8x22B Instruct or Mistral: Mistral Small 4?

Mistral: Mistral Small 4 has the larger context window (262K tokens).

Mistral: Mixtral 8x22B Instruct vs Mistral: Mistral Small 4

Q: Is Mistral: Mixtral 8x22B Instruct or Mistral: Mistral Small 4 cheaper?

Mistral: Mistral Small 4 is cheaper on output tokens ($0.60 vs $6.00 per 1M).

Mistral: Mistral Small 4 is cheaper on output tokens, while Mistral: Mistral Small 4 offers a larger context window. Choose Mistral: Mixtral 8x22B Instruct or Mistral: Mistral Small 4 based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Mistral: Mixtral 8x22B Instruct	Mistral: Mistral Small 4
Provider	Mistral	Mistral
Input / 1M tokens	$2.00	$0.15
Output / 1M tokens	$6.00	$0.60
Context window	66K	262K
Parameters	—	—
Open weights	—	—
Released	—	—

Mistral: Mixtral 8x22B Instruct details →Mistral: Mistral Small 4 details →

FAQ

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