CoralBricks

Agregador de Modelos

CoralBricks serves open models (GLM, DeepSeek) quantized to NVFP4 / MXFP4 on its own GPUs behind an OpenAI-compatible API (Chat Completions, Responses and background mode), billed per token in USD from prepaid credits. Cached input is billed at $0 on every model; novel input under prompt-cache retention bills at a separate cache-write rate.

Modelos
3
Caché de Prompts
✓
Descuento por Lotes
—
Tool Calling
✓
Modelo3
DeepSeek V4.1 FlashDeepSeek€0.2642€1.06
GLM 5.3GLM€0.9864€3.87
GLM 5.3 FlashGLM€0.1321€0.4403