Is All-MiniLM-L12-v2 or Qwen3.5 397B-A17B FP8 cheaper?

All-MiniLM-L12-v2 is cheaper on output tokens ($0.00 vs $4.46 per 1M).

Which has the larger context window, All-MiniLM-L12-v2 or Qwen3.5 397B-A17B FP8?

Qwen3.5 397B-A17B FP8 has the larger context window (200K tokens).

All-MiniLM-L12-v2 vs Qwen3.5 397B-A17B FP8

All-MiniLM-L12-v2 is cheaper on output tokens, while Qwen3.5 397B-A17B FP8 offers a larger context window. Choose All-MiniLM-L12-v2 or Qwen3.5 397B-A17B FP8 based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	All-MiniLM-L12-v2	Qwen3.5 397B-A17B FP8
Provider	Infomaniak	Infomaniak
Input / 1M tokens	$0.00	$0.99
Output / 1M tokens	$0.00	$4.46
Context window	128	200K
Parameters	—	—
Open weights	Yes	Yes
Released	Aug 2021	Feb 2026

All-MiniLM-L12-v2 details →Qwen3.5 397B-A17B FP8 details →

FAQ

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