Study: Anthropic models may be cheaper than some open-source Chinese models
rohanpaul_ai · x · 2026-08-15
A new study by AlphaSense suggests Anthropic models may be cheaper to use than some large open-source Chinese models. While Kimi is cheaper per token, it consumes many more tokens during context assembly, raising the total cost per question. The real cost metric is tokens-to-completion × token price. Efficient retrieval, stopping, and reasoning can lower the total inference bill. AlphaSense achieved a 3× cost reduction by optimizing retrieval, implying that controlling retrieval and routing decides economic viability.
More from Infra
- Running Qwen3.8-27B on 16GB VRAM: Q3_K_XL Benchmarks — No-Head2511 · 2026-08-15
- Tech Discussion: Why are 4bit GGUF Models Larger Than Expected? — gamesntech · 2026-08-15
- Polygres turns Postgres into extended context for AI agents — Scobleizer · 2026-08-15
- vLLM Introduces Adaptive Verification for Speculative Decoding with DSpark — vllm_project · 2026-08-15
- Open source closes the gap with closed labs: Quality gap now just months — togethercompute · 2026-08-15
- How Nuclear Will Unlock Energy Abundance with Valar Atomics Founder — No Priors · 2026-08-15