ModelPickr

Models / DeepSeek / DeepSeek V4 Flash 0423

DeepSeek · deepseek-flash

DeepSeek V4 Flash 0423

Initial DeepSeek V4 Flash snapshot for economical reasoning, coding, and million-token agent workloads

$0.14 in · $0.28 out

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

Provider input prices run from $0.14 to $0.19 per 1M tokens. Output prices run from $0.28 to $0.51.

Context
1,000,000
Max output
384,000
Cache read
$0.028
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Yes
Vision
No
Open weights
Yes
License
MIT
Released
Apr 23, 2026
Updated in source
Apr 23, 2026
Knowledge
2025-05
Providers
3

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
Merge Gateway$0.14$0.28———
NanoGPTreference$0.14$0.28$0.028——
Ofox$0.19$0.51$0.028——