Back to home
Back to home
Free tool · No signup

Egress Cost Predictor

In 2026, data movement between clouds often costs more than the AI inference itself. Teams pick a model on token price and get killed by network charges.

This pre-flight predictor flashes a warning before you build a $10k/mo cross-cloud pipeline. Rates pulled from public price pages (AWS $0.09/GB to internet · GCP $0.12/GB to other-cloud · Snowflake $40/TB).

Try a preset

Predict

MOVE THE MODEL

Egress is 76% of total cost. The data is bigger than the inference. Run inference IN GCP (provision the model there) instead of pulling the data out.

  • Use a GCP-native model endpoint (e.g. Bedrock for AWS, Vertex AI for GCP, Azure OpenAI for Azure)
  • OR: pre-aggregate / filter the data in GCP before sending only the inference-ready slice to AWS
Egress / month
$491.52
76.2% of total · $0.12/GB
Inference / month
$153.6
23.8% of total · 128.0M tokens/run
Total / month
$645.12
4 runs × $161.28
Cost composition per run
76.2% egress
23.8% inference
Pipeline GCPAWS · 1024 GB · 0.05% token budget · model gemini-3-flash

Egress rates ($/GB · Q1 2026)

Transparency · Public cloud egress price pages (AWS $0.09/GB to internet, GCP $0.12/GB to other-cloud, Azure $0.087/GB, Snowflake $40/TB compute pull). Refreshed quarterly.
FromTo$/GB
AWSAWS$0.02
AWSAZURE$0.09
AWSGCP$0.09
AWSINTERNET$0.09
AWSSAME-REGION$0
AZUREAWS$0.087
AZUREAZURE$0.02
AZUREGCP$0.087
AZUREINTERNET$0.087
AZURESAME-REGION$0
GCPAWS$0.12
GCPAZURE$0.12
GCPGCP$0.02
GCPINTERNET$0.12
GCPSAME-REGION$0
SNOWFLAKEAWS$0.13
SNOWFLAKEAZURE$0.127
SNOWFLAKEGCP$0.16

Wire into the LLM proxy

● Live in /api/llm-proxy

Pass 3 headers on any proxy call. If the predicted verdict is rose ("MOVE THE MODEL"), the proxy returns 412 Precondition Failed before forwarding to OpenAI/Anthropic — saving you both the egress and the inference cost.

curl -X POST https://proxy.cartieai.com/v1/chat/completions \
  -H "Authorization: Bearer $OPENAI_KEY" \
  -H "X-Cartie-Key: $CARTIE_KEY" \
  -H "X-Cartie-Source-Cloud: gcp" \
  -H "X-Cartie-Dest-Cloud: aws" \
  -H "X-Cartie-Data-GB: 1024" \
  -H "X-Cartie-Token-Budget-Pct: 0.05" \
  -H "X-Cartie-Egress-Enforce: true" \
  -d '{"model":"gemini-3-flash","messages":[...]}'

# Response when egress-dominant + enforce=true:
# HTTP/1.1 412 Precondition Failed
# { "error":"egress_preflight_blocked", "verdict":"MOVE THE MODEL", ... }

PR-time gate

Blocks any PR that adds an egress-dominant cross-cloud pipeline. Posts /api/egress/preflight-plan with the Terraform plan diff → aggregate verdict → CI exits non-zero on rose.

# .github/workflows/cartie-egress-gate.yml
# Blocks PRs that introduce egress-dominated cross-cloud pipelines.
name: Cartie Egress Gate
on:
  pull_request:
    paths:
      - 'terraform/**'
      - 'iac/**'

jobs:
  egress-gate:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4

      - name: Extract planned routes from terraform plan
        id: extract
        run: |
          # Your team's helper that turns a tf plan into the routes JSON.
          # Output shape: {"routes":[{"source_cloud":"gcp","dest_cloud":"aws",
          #   "data_gb":1024,"model":"gemini-3-flash","label":"summary_pipeline"}]}
          ./scripts/tf-plan-to-routes.sh > routes.json

      - name: Call Cartie egress preflight
        id: preflight
        run: |
          RESPONSE=$(curl -s -X POST "https://cartieai.com/api/egress/preflight-plan" \
            -H "Content-Type: application/json" \
            --data @routes.json)
          echo "$RESPONSE" | tee preflight.json
          SHOULD_BLOCK=$(echo "$RESPONSE" | jq -r .should_block)
          if [ "$SHOULD_BLOCK" = "true" ]; then
            echo "❌ Cartie blocked this PR — egress dominates."
            echo "$RESPONSE" | jq .blocked_reasons
            exit 1
          fi
          echo "✅ Cartie egress gate passed."

Want this as a real-time gate on every pipeline?

CARTIE wires the predictor into your PR checks. Cross-cloud egress over 30% of total cost? Merge is blocked.

We value your privacy. Cookies help us improve your experience. Learn more

Install CARTIE AI

Add to your home screen for quick access and offline support