Models / DeepSeek / DeepSeek V4 Flash Vision Exp

DeepSeek · deepseek-flash

DeepSeek V4 Flash Vision Exp

Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work

$0.22 in · $0.65 out

per 1M tokens · provider rate closest to the median. No first-party DeepSeek price was listed. The reference price is Kilo Gateway's rate, the provider closest to the median.

Provider input prices run from $0.08 to $0.57 per 1M tokens. Output prices run from $0.20 to $1.72.

Context
1,000,000
Max output
384,000
Cache read
$0.007
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Yes
Vision
Yes
Open weights
Yes
License
MIT
Released
Aug 21, 2026
Updated in source
Sep 1, 2026
Knowledge
—
Providers
17

Hugging Face weights

What this model costs per month

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Providers

Base rates from Models.dev. Where a provider lists the model more than once, the row is the listing whose id is closest to the canonical model id.
ProviderInputOutputCache readCache writeStatus
CrofAI$0.08$0.20$0.007——
AMD$0.14$0.28$0.003——
OpenCode$0.14$0.28$0.028——
OrcaRouter$0.15$0.30$0.02——
Eden AI$0.15$0.60$0.003——
OpenCode Go$0.15$0.60$0.003—deprecated
AIHubMix$0.16$0.62$0.003——
Kilo Gatewayreference$0.22$0.65$0.007——
OpenRouter$0.22$0.65$0.007——
Vercel AI Gateway$0.22$0.65$0.007——
NanoGPT$0.22$0.66$0.007——
CrossModel$0.30$1.20$0.006$0.30—
Deep Infra$0.44$1.32$0.014——
Hugging Face$0.44$1.32———
Ofox$0.44$1.32$0.014—beta
SiliconFlow$0.44$1.32$0.028——
AI/ML API$0.57$1.72$0.018——

Jobs this model qualifies for