Loading…
DeepSeek
deepseek/deepseek-v4-flash-vision-expHugging Face ↗
DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...
Only tracked on Vercel AI Gateway.
Vercel AI Gateway share of tokens, by day.
DeepSeek V4 Flash Vision Exp holds 2.28% today, up from 0.07% at the start of the visible window.
DeepSeek V4 Flash Vision Exp's share plotted against days since first tracked, overlaid on other current leaders on the same axis. The question every new-model page asks: is this one going to make it?
Citable stat
As of 2026-10-15, DeepSeek V4 Flash Vision Exp holds 0.0% of Vercel AI Gateway token share, down 2.28pp over 30 days. Data: Vercel AI Gateway as of 2026-10-15. tidelines.ai
Where to run it
Per-provider pricing, context, and uptime via OpenRouter. Sorted by output price.
DeepSeek V4 Flash Vision Exp is served by 3 tracked endpoints on OpenRouter. The cheapest output price is $0.65 per million tokens from DeepInfra, and the most expensive is $1.32 from SiliconFlow. The largest context window offered is 1049k tokens. Prices are list rates and refresh daily.
| Provider | Input $/M | Output $/M | Context | Uptime |
|---|---|---|---|---|
| DeepInfra | $0.22 | $0.65 | 1049k | 100.00% |
| GMICloud | $0.44 | $1.32 | 1049k | — |
| SiliconFlow | $0.44 | $1.32 | 1049k | 100.00% |
Median dollars spent on one DeepSeek V4 Flash Vision Exp session, by coding agent and session length.
Token rate sets the price; session length and reasoning set the bill.
| Agent | 1 turn | 2–9 turns | 10–49 turns | 50+ turns |
|---|---|---|---|---|
| Hermes Agent | $0.0016 | $0.0082 | $0.067 | $0.400 |
