Inference.net API
Inference.net is a platform for running large language models in the cloud.
Data & Privacy
HQ:US
Safety identifier:Not forwarded
API Training:Unknown
Prompt Logging:Unknown
Retention:Unknown
SOC2:Type II Certified
Available Models
DeepSeek V4.1 Flash Cyber
deepseek
deepseek-v4.1-flash-cyberStreaming
Vision
Tools
Reasoning
JSON Output
JSON Schema
Inference.net
Context: 1.0M
Input
$0.3
/M tokens
Cached
$0.007
/M tokens
Output
$1
/M tokens
MiniMax M3.1 Flash
minimax
minimax-m3.1-flashStreaming
Vision
Tools
Reasoning
JSON Output
Inference.net
Context: 1M
Input
$0.1
/M tokens
Cached
$0.005
/M tokens
Output
$0.5
/M tokens
DeepSeek V4.1 Flash 1017
deepseek
deepseek-v4.1-flash-1017Streaming
Vision
Tools
Reasoning
JSON Output
JSON Schema
Inference.net
Context: 262.1k
Input
$0.3
/M tokens
Cached
$0.007
/M tokens
Output
$1
/M tokens
GLM-5.3 Flash
zai
glm-5.3-flashStreaming
Vision
Tools
Reasoning
JSON Output
JSON Schema
Inference.net
Context: 1.0MQuant: fp4
Input
$0.09
/M tokens
Cached
$0.02
/M tokens
Output
$0.28
/M tokens
GLM-5.3
zai
glm-5.3Streaming
Tools
Reasoning
JSON Output
JSON Schema
Inference.net
Context: 1.0MQuant: fp4
Input
$0.9
/M tokens
Cached
$0.15
/M tokens
Output
$3
/M tokens
Llama 3.2 11B Instruct
meta
llama-3.2-11b-instructStreaming
JSON Output
Inference.net
Context: 128k
Input
$0.07
/M tokens
Cached
—
/M tokens
Output
$0.33
/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-cyber. On pay-as-you-go keys, inference.net/deepseek-v4.1-flash-cyber pins every request to Inference.net; DevPass coding plans do not support provider pinning. You do not need a separate Inference.net account or SDK.