Self-hosted MiniMax H3 renders for $0.03, compared to fal's faster H3 Max
tobowers · x · 2026-08-27
A developer compared self-hosted MiniMax H3 with fal.ai's H3 Max for video generation. Using a rented Nebius H200 GPU with NVIDIA Sol-Attn optimizations, the self-hosted H3 in 'draft' mode renders extremely cheaply ($0.03, 13s), while H3 Max is faster and higher quality but much more costly. The post details performance under identical prompts, noting that cheap draft iterations open new possibilities.
More from Infra
- SGLang ships Day-0 support for FLUX 3 Image Klein: 10 reference images, BF16/FP8/NVFP4 variants — ying11231 · 2026-10-16
- NVIDIA's Nemotron 3.5 Super VL hits CoreWeave: 12B-active multimodal MoE at $0.25/M input tokens — wandb · 2026-10-16
- Chip equipment beats bull case: 2026 WFE seen at $153B, $278B by 2030 — BenBajarin · 2026-10-16
- Steam now launches in 5.23s, beating Epic's 5.47s — and vLLM gets roasted for slow startup — AlpinDale · 2026-10-16
- Shadeform to Announce Six New Features on Oct 19: Lower GPU Costs, More Suppliers — _jaydeepkarale · 2026-10-16
- Fastino launches Training API for SFT/RL, claiming 25-85% cost cut vs Tinker — kalyan_kpl · 2026-10-16