DeepSeek
DeepSeek V4 Flash
deepseek/deepseek-v4-flashHugging Face ↗
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
Only tracked on Vercel AI Gateway.
DeepSeek V4 Flash usage over time
Vercel AI Gateway share of tokens, by day.
DeepSeek V4 Flash holds 15.52% today, up from 13.82% at the start of the visible window.
Rank history
Adoption curve vs the pantheon
DeepSeek V4 Flash'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 2026-07-17, DeepSeek V4 Flash holds 15.5% of Vercel AI Gateway token share, down 1.38pp over 30 days. Source: Tidelines (Vercel AI Gateway).
Where to run it
Providers & pricing
Per-provider pricing, context, and uptime via OpenRouter. Sorted by output price.
| Provider | Input $/M | Output $/M | Context | Uptime |
|---|---|---|---|---|
| DeepInfra | $0.09 | $0.18 | 1049k | 99.58% |
| StreamLake | $0.10 | $0.19 | 1024k | 98.49% |
| GMICloud | $0.10 | $0.20 | 1049k | 99.11% |
| Baidu | $0.10 | $0.20 | 1049k | 99.92% |
| DigitalOcean | $0.11 | $0.22 | 262k | 99.96% |
| Alibaba | $0.13 | $0.27 | 1000k | 99.90% |
| Venice | $0.14 | $0.28 | 1000k | 99.89% |
| Morph | $0.14 | $0.28 | 1049k | 97.30% |
| SiliconFlow | $0.13 | $0.28 | 1049k | 99.86% |
| Parasail | $0.14 | $0.28 | 1049k | 99.44% |
| Fireworks | $0.14 | $0.28 | 1049k | 96.31% |
| Novita | $0.14 | $0.28 | 1049k | 99.99% |
| WandB | $0.14 | $0.28 | 1049k | 99.70% |
| AkashML | $0.14 | $0.28 | 131k | 99.85% |
| AtlasCloud | $0.14 | $0.28 | 1049k | 99.74% |
| DeepSeek | $0.14 | $0.28 | 1049k | 99.99% |
| NextBit | $0.18 | $0.34 | 1049k | 99.93% |
| Io Net | $0.25 | $0.40 | 1049k | 99.28% |