Command Palette

Search for a command to run...

DeepSeek V3.1 (Non-reasoning)

DeepSeek

MIT

Analysis of DeepSeek's DeepSeek V3.1 (Non-reasoning) and comparison to other AI models across key metrics including quality, price, performance (tokens per second & time to first token), context window & more.

Context

Release Date
Aug 21, 2025
Window
128k

PricingPer 1M tokens

Input
$0.555
Output
$1.67
Blended 3:1
$0.8338

Capabilities

Input
Output
Reasoning tokens

Benchmarks

Intelligence
●○○○○
Math
●●○○○
Coding
●○○○○
MMLU Pro
83.3%
GPQA
73.5%
HLE
6.3%
SciCode
36.7%
AIME
49.7%
LiveCodeBench
57.7%

Analysis of DeepSeek's DeepSeek V3.1 (Non-reasoning) and comparison to other AI models across key metrics including quality, price, performance (tokens per second & time to first token), context window & more.