Is Mistral: Codestral 2508 or DeepSeek: R1 cheaper?

Mistral: Codestral 2508 is cheaper on output tokens ($0.90 vs $2.50 per 1M).

Which has the larger context window, Mistral: Codestral 2508 or DeepSeek: R1?

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

Mistral: Codestral 2508 vs DeepSeek: R1

Mistral: Codestral 2508 is cheaper on output tokens, while Mistral: Codestral 2508 offers a larger context window. Choose Mistral: Codestral 2508 or DeepSeek: R1 based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Mistral: Codestral 2508	DeepSeek: R1
Provider	Kilo Gateway	Kilo Gateway
Input / 1M tokens	$0.30	$0.70
Output / 1M tokens	$0.90	$2.50
Context window	256K	64K
Parameters	—	671B
Open weights	Yes	Yes
Released	Aug 2025	Jan 2025

Mistral: Codestral 2508 details →DeepSeek: R1 details →

FAQ

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