Is Codestral 2508 or Qwen3.5 397B A17B cheaper?

Codestral 2508 is cheaper on output tokens ($0.90 vs $3.60 per 1M).

Which has the larger context window, Codestral 2508 or Qwen3.5 397B A17B?

Codestral 2508 has the larger context window (256K tokens).

Codestral 2508 vs Qwen3.5 397B A17B

Codestral 2508 is cheaper on output tokens, while Codestral 2508 offers a larger context window. Choose Codestral 2508 or Qwen3.5 397B A17B based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Codestral 2508	Qwen3.5 397B A17B
Provider	Cortecs	Cortecs
Input / 1M tokens	$0.30	$0.60
Output / 1M tokens	$0.90	$3.60
Context window	256K	250K
Parameters	—	397B
Open weights	Yes	Yes
Released	Jul 2025	Feb 2026

Codestral 2508 details →Qwen3.5 397B A17B details →

FAQ

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