Sciforium API
Sciforium runs open-weight models on its own AMD GPU infrastructure delivering faster and cost effective inference with an OpenAI-compatible API.
Data & Privacy
HQ:US
Safety identifier:Not forwarded
API Training:No
Prompt Logging:No
Retention:None
GDPR:Unknown
ISO 27001:Unknown
Available Models
Pricing and availability as of
DeepSeek V4.1 Flash 1017
deepseek
deepseek-v4.1-flash-1017Streaming
Vision
Tools
Reasoning
JSON Output
JSON Schema
Context: 1.0MQuant: fp8
Input
$0.2
/M tokens
Cached
$0.004
/M tokens
Output
$0.8
/M tokens
deepseek-v4.1-flash-latest
deepseekVirtual model
deepseek-v4.1-flash-latestStreaming
Vision
Tools
Reasoning
JSON Output
JSON Schema
Context: 1.0MQuant: fp8
Input
$0.2
/M tokens
Cached
$0.004
/M tokens
Output
$0.8
/M tokens
Create an LLM Gateway API key and point any OpenAI-compatible SDK at https://api.llmgateway.io/v1. Set the model to deepseek-v4.1-flash-1017. On pay-as-you-go keys, sciforium/deepseek-v4.1-flash-1017 pins every request to Sciforium; DevPass coding plans do not support provider pinning. You do not need a separate Sciforium account or SDK.