DeepSeek

DeepSeek V4 Flash Vision Exp

CTX1M

NewRetired

Reasoning · Vision · Tools

Input$0.15/M

Output$0.60/M

October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding

Open weightsMIT1039/1040

Drag to turn

DeepSeekTextCommonRetired

DeepSeek V4 Flash Vision Exp

October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding

deepseek-v4-flash-vision-exp

Type: Text
Quality: Not rated yet
Context window: 1,000,000 tokens
Max output: 393,216 tokens
Input price: $0.15 / 1M tokens
Output price: $0.60 / 1M tokens
Cache read: $0.003 / 1M tokens
Cache write: —
Parameters: 305B (304,646,824,126)
Downloads: 500K in the last 30 days
Likes: 950
Access to weights: Open download
Released: Oct 17, 2026
Knowledge cutoff: May 2025
Takes in: Text, Image
Puts out: Text
Reasoning: Yes
Tool calling: Yes
Structured output: Yes
File attachments: Yes
Access: Open weights
License: MIT
Rarity: Common
Set number: 1039/1040

Open DeepSeek docs Weights on Hugging Face Where to run it 18 Meet its creature Battle Mistral Small 4

License read from the model’s Hugging Face card. Specs from models.dev, downloads from Hugging Face, last changed Oct 18, 2026. Official source: api-docs.deepseek.com.

How good is it?

Public leaderboard scores for DeepSeek V4 Flash Vision Exp, refreshed daily from Epoch AI and LMArena.

No public leaderboard lists DeepSeek V4 Flash Vision Exp yet. Epoch AI and LMArena cover most chat, image, and video models from the big labs; embeddings, speech, and small open models mostly go unrated.

Where to run it

17 providers sell DeepSeek V4 Flash Vision Exp through an API, and 1 Hugging Face host serves it. Prices are per million tokens, cheapest first.

CheapestCrofAI$0.08 in · $0.20 out
From the labDeepSeek$0.15 in · $0.60 out
Fastest on Hugging FaceDeepInfra137 tokens/s

API providers

Provider	Input	Output	Context
CrofAICheapest paid`deepseek-v4-flash-vision-exp`	$0.08	$0.20	1M
AMD`DeepSeek-V4-Flash-Vision-Exp`	$0.14	$0.28	1M
OpenCode`deepseek-v4-flash-vision-exp`	$0.14	$0.28	1M
OrcaRouter`deepseek/deepseek-v4-flash-vision-exp`	$0.15	$0.29	1M
CommandCode`deepseek/deepseek-v4-flash-vision-exp`	$0.15	$0.60	1M
DeepSeekOfficial`deepseek-v4-flash-vision-exp`	$0.15	$0.60	1M
Eden AI`deepseek-v4-flash-vision-exp`	$0.15	$0.60	1M
AIHubMix`deepseek-v4-flash-vision-exp`	$0.15	$0.62	1M
Kilo Gateway`deepseek/deepseek-v4-flash-vision-exp`	$0.22	$0.65	1.05M
NanoGPT`deepseek/deepseek-v4-flash-vision-exp`	$0.22	$0.65	1.05M

Show 7 more providers

Provider	Input	Output	Context
OpenRouter`deepseek/deepseek-v4-flash-vision-exp`	$0.22	$0.65	1.05M
Vercel AI Gateway`deepseek/deepseek-v4-flash-vision-exp`	$0.22	$0.65	1.05M
CrossModel`deepseek/deepseek-v4-flash-vision-exp`	$0.30	$1.20	1M
Deep Infra`deepseek-ai/DeepSeek-V4-Flash-Vision-Exp`	$0.44	$1.32	1.05M
Ofox`deepseek/deepseek-v4-flash-vision-exp`	$0.44	$1.32	1M
SiliconFlow`deepseek-ai/DeepSeek-V4-Flash-Vision-Exp`	$0.44	$1.32	1M
AI/ML API`deepseek/deepseek-v4-flash-vision-exp`	$0.57	$1.72	1.05M

Hugging Face Inference Providers

Host	Input	Output	Context	Speed	First token
DeepInfraTools	$0.44	$1.32	1.05M	137 tok/s	0.3s

From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.

Face off

Current text models from other labs at a similar output price.