CoralBricks

Model Aggregator

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.

Models
3
Prompt Caching
✓
Batch Discount
—
Tool Calling
✓
Model3
DeepSeek V4.1 FlashDeepSeek$0.3$1.2
GLM 5.3GLM$1.12$4.4
GLM 5.3 FlashGLM$0.15$0.5