跳到主要内容

RanoAI API

RanoAI serves open-weight large language models on Furiosa RNGD NPU hardware via an OpenAI-compatible inference API.

Data & Privacy

HQ:US
Safety identifier:Not forwarded
API Training:No
Prompt Logging:No
Retention:0 days

Available Models

DeepSeek V4 Flash

deepseek
deepseek-v4-flash
Streaming
Tools
Reasoning
JSON Schema
RanoAI
Context: 1MQuant: fp4
Input
$0.14
/M tokens
Cached
$0.028
/M tokens
Output
$0.28
/M tokens

FAQ

RanoAI API questions

需要更多帮助?请登录本实例的控制台查看说明,登录控制台。

Create a China OpenRouter API key and point any OpenAI-compatible SDK at https://p.nat6.net/v1. Set the model to deepseek-v4-flash. On pay-as-you-go keys, ranoai/deepseek-v4-flash pins every request to RanoAI; DevPass coding plans do not support provider pinning. You do not need a separate RanoAI account or SDK.