Ultra-fast inference platform powered by custom LPU hardware for low-latency AI.
| Model |
|---|
Qwen/Qwen3.8-27Bqwen/qwen3.8-27b |
GPT OSS 120BOSSopenai/gpt-oss-120b |
GPT OSS 20BOSSopenai/gpt-oss-20b |
MiniMax M2.7 Enterpriseminimaxai/minimax-m2.7 |
Whisper Large V3 Turbowhisper-large-v3-turbo |
Canopy Labs Orpheus V1 Englishcanopylabs/orpheus-v1-english |
Canopy Labs Orpheus Arabic Saudicanopylabs/orpheus-arabic-saudi |
Whisperwhisper-large-v3 |
Prompt Guard 2 86Mmeta-llama/llama-prompt-guard-2-86m |
Llama Prompt Guard 2 22Mmeta-llama/llama-prompt-guard-2-22m |