Providers

GMI Cloud

A GPU cloud provider serving open-weight models on dedicated NVIDIA infrastructure.

Models on GMI Cloud

Open in catalog

5 of 5

Claude Haiku 4.5Chatclaude-haiku-4.5200K contextRouteemergency$1.00 / $5.00per M input / output
Claude Opus 4.6Chatclaude-opus-4.6200K contextRoutefallback$5.00 / $25.00per M input / output
GLM-5Chatglm-5128K contextWeights Routeemergency$1.00 / $3.20per M input / output
Kimi K2.5Chatkimi-k2.5262K contextRouteprimary$0.60 / $3.00per M input / output
MiniMax M2.5Chatminimax-m2.5197K contextRoutefallback$0.30 / $1.20per M input / output
Direct routingCall GMI Cloud explicitly
gmicloud· routing
# pin every request to GMI Cloud
curl https://www.ninjachat.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $NINJACHAT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k2.5",
    "messages": [{ "role": "user", "content": "Hello!" }],
    "routing": { "providers": { "only": ["gmicloud"] } }
  }'