RanoAI Provider
RanoAI serves open-weight large language models on Furiosa RNGD NPU hardware via an OpenAI-compatible inference API.
Data & Privacy
HQ:US
API Training:No
Consumer Training:No
Prompt Logging:No
Retention:0 days
Available Models
Gemma 4 31B IT
google
gemma-4-31b-itStreaming
Vision
Tools
Reasoning
JSON Output
JSON Schema
RanoAI
Context: 20.5k
Input
$0.1
/M tokens
Cached
$0.05
/M tokens
Output
$0.3
/M tokens