GMI Cloud Provider
GMI Cloud provides OpenAI-compatible serverless inference for open-weight and frontier models on NVIDIA GPU infrastructure.
Available Models
GLM-5.3 Flash
glm50% off
glm-5.3-flashStreaming
Vision
Tools
Reasoning
JSON Output
50% Discount
GMI Cloud
Context: 1.0M50% off
Input
$0.15$0.075
/M tokens
Cached
$0.03$0.015
/M tokens
Output
$0.5$0.25
/M tokens
TCS Cheap
tcs50% off
tcs-cheapStreaming
Vision
Tools
Reasoning
JSON Output
50% Discount
GMI Cloud
Context: 1.0M50% off
Input
$0.15$0.075
/M tokens
Cached
$0.03$0.015
/M tokens
Output
$0.5$0.25
/M tokens
TCS Balanced
tcs50% off
tcs-balancedStreaming
Vision
Tools
Reasoning
JSON Output
50% Discount
GMI Cloud
Context: 1.0M50% off
Input
$0.15$0.075
/M tokens
Cached
$0.03$0.015
/M tokens
Output
$0.5$0.25
/M tokens
TCS Vision
tcs50% off
tcs-visionStreaming
Vision
Tools
Reasoning
JSON Output
50% Discount
GMI Cloud
Context: 1.0M50% off
Input
$0.15$0.075
/M tokens
Cached
$0.03$0.015
/M tokens
Output
$0.5$0.25
/M tokens