LLM Comparison

DeepSeek V3.1 Terminus vs Devstral 2 2512

Side-by-side specs, pricing & capabilities · Updated April 2026

Add to comparison

2/6 models

Same tier:

	D DeepSeek V3.1 Terminus	D Devstral 2 2512
Organization	DeepSeek	Mistral AI
OpenTools Score	75 150
Family	DeepSeek	Devstral
Status	Current	Current
Release Date	Sep 2025	Dec 2025
Context Window	164K tokens	262K tokens
Input Price	$0.21/M tokens	$0.40/M tokens
Output Price	$0.79/M tokens	$2.00/M tokens
Pricing Notes	Cache read: $0.1300/M tokens	Cache read: $0.0400/M tokens
Capabilities	textcode	textcodetool-use
API Identifier	`deepseek/deepseek-v3.1-terminus`	`mistralai/devstral-2512`
Benchmarks
MMLU	87.1openrouter	—
HumanEval	89.2openrouter	—
MATH	90.2openrouter	—
	View DeepSeek V3.1 Terminus	View Devstral 2 2512

Cost Calculator

Enter your expected monthly token usage to compare costs.

Input tokens / month

Output tokens / month

Model	Input	Output	Total / mo	vs Best
DeepSeek V3.1 TerminusCheapest	$0.21	$0.40	$0.61	—
Devstral 2 2512	$0.40	$1.00	$1.40	+131%

DeepSeek

DeepSeek V3.1 Terminus

DeepSeek V3.1 Terminus is a large language model from DeepSeek. Supports up to 163,840 token context window. Achieves 87.1% on MMLU. Available from $0.21/M input tokens.

Mistral AI

Devstral 2 2512

Devstral 2 2512 is a large language model from Mistral AI. Supports up to 262,144 token context window. Available from $0.40/M input tokens.