Ollama launches off-peak pricing: DeepSeek-V4 models half price nights and weekends
ollama · x · 2026-09-06
Ollama officially introduced off-peak token rates for its cloud inference: DeepSeek-V4-Flash and Pro are half price outside 12:00–18:00 UTC on weekdays (5–11am Pacific) and all day on weekends. More models will get off-peak pricing soon.
Regular per-million-token prices: deepseek-v4-flash at $0.22 input / $0.66 output, deepseek-v4-pro at $0.66 / $1.98, alongside gemma4, glm-5.x, kimi-k3, minimax and qwen3.5:397b. DeepSeek models are hosted in the US and Europe with zero data retention (ZDR). Subscription tiers include Free, Pro ($20/mo), Max ($100/mo) and Team ($500/mo).
Related event: Ollama Cloud Cuts DeepSeek-V4 Token Prices in Half Off-Peak(2 posts)→
More from Infra
- Jensen Huang visits Astana, joins Kazakhstan's AI minister to discuss nation's AI future — nvidia · 2026-10-23
- FP16 vs FP32 matmul on RTX 4060: 3.5x speedup at large sizes, slower at 128x128 — cneuralnetwork · 2026-10-23
- BaseQuant V1 quants for agentic Qwen3.8-27B hit 17-34% lower KL than Unsloth — nightowlsleeping · 2026-10-23
- PhD students in some countries get B200s on demand, unlike their US peers — HildeKuehne · 2026-10-23
- Nvidia's Berlin GTC spotlights humanoid robots and Vera Rubin AI supercomputing — emmanuelvivier · 2026-10-23
- Lenovo adds 5 AI Library use cases, claims 1-week deployment and up to 70% lower token cost — shashib · 2026-10-23