API & integrations

# Install
uv tool install "together[cli]"

# List commands
tg --help

export TOGETHER_API_KEY=<your_key>

tg beta clusters create \
  --name my-cluster \
  --num-gpus 8 \
  --gpu-type H100_SXM \
  --region us-central-8 \
  --billing-type ON_DEMAND \
  --cluster-type KUBERNETES

# Reserved capacity
tg beta clusters create \
  --name my-cluster \
  --num-gpus 8 \
  --gpu-type H100_SXM \
  --region us-central-8 \
  --billing-type RESERVED \
  --duration-days 30 \
  --cluster-type KUBERNETES

# On-demand capacity
tg beta clusters create \
  --name my-cluster \
  --num-gpus 8 \
  --gpu-type H100_SXM \
  --region us-central-8 \
  --billing-type ON_DEMAND \
  --cluster-type KUBERNETES

tg beta clusters delete [CLUSTER_ID]

tg beta clusters list

tg beta clusters update [CLUSTER_ID] --num-gpus 16

tg beta clusters get-credentials [CLUSTER_ID] --set-default-context

uv pip install skypilot[kubernetes]

tg beta clusters get-credentials [CLUSTER_ID] --set-default-context

sky check k8s

Checking credentials to enable infra for SkyPilot.
  Kubernetes: enabled [compute]
    Allowed contexts:
    └── t-51326e6b-25ec-42dd-8077-6f3c9b9a34c6-admin: enabled.

🎉 Enabled infra 🎉
  Kubernetes [compute]

sky show-gpus --infra k8s

resources:
  accelerators: H100:8
  cloud: kubernetes

setup: |
  pip install torch transformers

run: |
  python train.py

sky launch -c my-job task.yaml

sky launch -c gpt-together gpt-oss-20b.yaml

name: Train Model

on: push

jobs:
  train:
    runs-on: ubuntu-latest
    env:
      TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
    steps:
      - uses: actions/checkout@v3

      - name: Install the Together CLI
        run: uv tool install "together[cli]"

      - name: Create GPU Cluster
        run: |
          tg beta clusters create \
            --name training-${{ github.sha }} \
            --num-gpus 8 \
            --billing-type ON_DEMAND \
            --gpu-type H100_SXM \
            --region us-central-8 \
            --cluster-type KUBERNETES \
            --non-interactive

      - name: Run Training
        run: |
          # Submit training job to cluster
          kubectl apply -f training-job.yaml

      - name: Cleanup
        if: always()
        run: |
          tg beta clusters delete [CLUSTER_ID]

# Create cluster daily at 6 AM for batch processing
0 6 * * * tg beta clusters create \
  --name daily-batch \
  --num-gpus 16 \
  --billing-type ON_DEMAND \
  --gpu-type H100_SXM \
  --region us-central-8 \
  --cluster-type KUBERNETES \
  --non-interactive

# Scale based on job queue length
if [ "$JOB_QUEUE_LENGTH" -gt 100 ]; then
  tg beta clusters update [CLUSTER_ID] --num-gpus 16
else
  tg beta clusters update [CLUSTER_ID] --num-gpus 8
fi