DeepSeek V4 Flash Vision

DeepSeekReleased Aug 21, 2026

DeepSeek V4 Flash Vision is not ranked on LMArena yet; output price $1.32 per 1M tokens.

Key metrics

Arena score–Not yet rated
Intelligence34.8Variant: max
Coding65.0Artificial Analysis
List price in / out$0.44 / $1.32USD per 1M tokens
Lowest route–Cheapest OpenRouter route
Context–tokens
Output speed221tok/sAA measured median
TTFT / first answer0.9 / 9.9sReasoning model: includes thinking

More from DeepSeek

#ModelArenaIntel.Output $tok/s
30DeepSeek V4.1 Flash1462.439.5$1.20219
39DeepSeek V4 Pro1451.136.0$3.96100
57DeepSeek V4 Flash1432.134.3$1.32–
62DeepSeek V3.21424.516.0$0.42–
–DeepSeek V4 Pro 0424–30.1$0.87–

Pricing

  • Official API list price: $0.44 input and $1.32 output per 1M tokens (USD).
  • At a typical 3:1 input-to-output ratio, the blended cost is about $0.66 per 1M tokens.
  • Among 78 models with an output price, it is the #16 cheapest.

Sources & methodology

DeepSeek V4 Flash Vision (DeepSeek): Intelligence Index 34.8, $0.44 in / $1.32 out per 1M tokens. Data updated Oct 9, 2026.

  • LMArena — Arena score, 95% confidence interval, votes and rank.
  • Artificial Analysis — Intelligence / Coding Index, output speed and latency (medians).
  • OpenRouter — Route prices, context length and listing date.

Arena scores use the Bradley-Terry model (not Elo); ± is the half-width of the 95% confidence interval. Latency figures are Artificial Analysis medians; for reasoning models, time to first token and to first answer include the thinking phase. Data syncs daily at 14:20 (UTC+8).

FAQ

What rank is DeepSeek V4 Flash Vision right now?

DeepSeek V4 Flash Vision has not been scored by LMArena yet, so it is not ranked here.

What does DeepSeek V4 Flash Vision cost via API?

Input $0.44 / output $1.32 per 1M tokens (official API list price; the OpenRouter quote when no official price is available). At a typical 3:1 input-to-output ratio, the blended cost is about $0.66 per 1M tokens.

How fast is DeepSeek V4 Flash Vision?

Artificial Analysis measures about 221 output tokens per second, 0.9 s to the first token and 9.9 s to the first answer token; it is a reasoning model, so latency includes thinking time.

Is DeepSeek V4 Flash Vision open source? Can it be self-hosted?

DeepSeek V4 Flash Vision is a closed model, available only via official APIs or hosted services.

Related leaderboards