deepseek-v4-flash

1435 Score third-party Elo · arena.ai / LMArena ?

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...

LLM & Generative AI 1 model 2 listings snapshot Oct 14, 2026, 12:43 AM

Platforms

click a card to open the detail table

Cheapest DeepInfra no official benchmark Input$0.090 Output$0.180 per 1M tokens Fastest OpenRouter lowest p50 latency on this board 128.1 ms p50 Most free quota — largest published free allowance — free tier

Model variants

W3r9 dedup — same model + identical tags merge; prices are listed per billing form

Model	Provider	Tags	Input /1M	Output /1M
deepseek/deepseek-v4-flash	OpenRouter	1M contextreasoning	$0.091	$0.182
deepseek-ai/DeepSeek-V4-Flash	DeepInfra	1M contextreasoning	$0.090	$0.180

Capabilities

official design_arena & architecture metadata

Design Arena Elo official design_arena benchmark (OpenRouter)

website 1210 · 49.1% wr
codecategories 1208 · 48.9% wr
gamedev 1202 · 50.2% wr
3d 1190 · 49.3% wr
uicomponent 1166 · 44.7% wr
svg 1155 · 48.4% wr
dataviz 1129 · 40.7% wr
asciiart 1113 · 42.8% wr

Input / Output modalities modality: text->text

text in+out

Platform details

per provider

provider	model	Input /1M	Output /1M	Latency ?	Official $/1M	Availability	Data time
DashScope	deepseek-v4-flash-0731	$0.222	$0.667	—	—	—	2026-10-14 00:53:13
DeepInfra	deepseek-ai/DeepSeek-V4-Flash-Vision-Exp	$0.440	$1.32	—	—	—	2026-10-14 00:43:44
Novita	deepseek/deepseek-v4-flash-0731	$0.440	$1.32	—	—	—	2026-10-14 00:54:15
OpenRouter	deepseek/deepseek-v4-flash-vision-exp	$0.216	$0.647	128.1 ms	—	100% available	2026-10-14 00:43:21
Together	deepseek-ai/DeepSeek-V4-Flash-0731	$0.140	$0.280	—	—	—	2026-10-14 00:53:13

5 rows · snapshot 2026-10-14 00:43:44 · from data/public/prices.json + measurements.json