Catalog
Models the network serves right now
Use the id as the model field in any request. Prices are per 1M tokens; models with no price are free.
Sort:
3 of 3
Auto Router · auto
free
Auto-router: picks a connected model for each request; you pay the rate of the model it picked.
Qwen3.5-9B (GGUF Q4_K_M) · Alibaba / Qwen (GGUF: unsloth)
free
llama.cpp GGUF build (Q4_K_M) of Qwen3.5-9B - one artifact runs on Metal, CUDA and CPU; the build the GGUF consensus engine was proven on.
Qwen3.8-27B (GGUF UD-Q4_K_M) · Alibaba / Qwen (GGUF: unsloth)
free
llama.cpp GGUF build (Unsloth Dynamic Q4_K_M) of Qwen3.8-27B - one artifact runs on Metal, CUDA and CPU. 262144-token context. The upstream model is multimodal (image-text-to-text); this pin covers the TEXT weights only - the vision projector (mmproj) is a separate artifact and is not part of this manifest.