OpenRouter Blog13 min read
LLM Quantization: What fp8 and fp4 Do to Quality and Price
When you call an open-weight model through an API, several providers may serve it at different precisions, such as 16-bit bf16, 8-bit fp8 or 4-bit fp4. The precision can affect both the answers and the price.
By OpenRouterOpenRouter Blog

Read the full story
Originally published by OpenRouter Blog on Nov 11, 2026.
Comments
Sign in to join the discussion.