Inside DeepSeek's Price Hike: Compute Strained, Seeks $5.6B Funding at $55.6B Valuation
量子位 · wechat · 2026-08-07
DeepSeek has announced a significant price hike for its model APIs, primarily driven by overwhelming usage that has strained its compute capacity. Following the launch of its V4-Flash model, global call volumes have skyrocketed; on the OpenCode platform alone, daily calls exceeded 8 trillion tokens. Furthermore, agentic workloads inherently trigger multi-turn reflections and tool usage, causing token consumption per task to grow exponentially.
This price increase is not an isolated incident; other major Chinese model providers like Zhipu and Moonshot have also recently raised prices due to supply shortages. To address the compute crisis, DeepSeek is building a 1-gigawatt data center in Inner Mongolia. Concurrently, reports indicate the company has restarted a new funding round aiming to raise 50 billion RMB (approx. $5.6B) with a pre-money valuation of around 500 billion RMB (approx. $55.6B), alongside preparations for an A-share IPO.
More from Venture
- Indie hacker tip: submitting your sitemap to GSC got 6,021 pages indexed in 2 days — alexmacgregor__ · 2026-10-16
- Grok-built linear regression bot claims $508K PnL in 125 days on Polymarket — Roger_M_Taylor · 2026-10-16
- Pay-to-rank directory outbid.lol charges $20 a day for the #1 spot, top listings paid $14k-17k — jonathan_wilke · 2026-10-16
- SignWith, a pay-per-doc e-signature tool, hits 1,000+ non-tech businesses — tibo_maker · 2026-10-16
- After 6,000 tweets and a $10M exit, tibo shares data on what works on X — tibo_maker · 2026-10-16
- Decision Models spins out its sandboxing system as a cheap standalone product — airesearch12 · 2026-10-16