Modal logo
Introduction Functions Functions Invocation methods Function lookups Container lifecycle management Parametrized Functions Dynamic configuration Sandboxes Sandboxes Running commands Networking and security File access Snapshots Pricing and resources VM Sandboxes BetaSidecars AlphaImages Defining Images Using existing container images Named images Fast pull from registry GPUs and other resources GPU acceleration Using CUDA on Modal Configuring CPU, memory, and disk Scaling out Scaling out Input concurrency Batch processing Job queues Dynamic batching Multi-node clusters BetaDeployment Apps, Functions, and entrypoints Managing deployments Continuous deployment Scheduled Functions Endpoints Endpoints Endpoint metrics Benchmark an endpoint Endpoint integrations HTTP Applications Servers Web Functions Streaming endpoints Web Function URLs Request timeouts Proxy Tokens Networking Tunnels Proxies BetaCluster networking Data sharing and storage Passing local data Volumes Storing model weights Cloud bucket mounts Dicts Queues Dataset ingestion Secrets and environment variables Secrets Environment variables Performance Cold start performance Memory Snapshots High-performance LLM inference Reliability and robustness Failures and retries Preemption Timeouts GPU health Troubleshooting Security and privacy Security and privacy Data residency Customer-supplied encryption keys AlphaAudit logs Integrations Using OIDC to authenticate with external services Connecting Modal to your Datadog account Connecting Modal to your OpenTelemetry provider Okta SSO Microsoft Entra SSO Custom SAML SSO SCIM Integration BetaSlack notifications BetaWorkspace & account settings Workspaces Environments Modal user account setup Service users Role-Based Access Control (RBAC) Billing Network egress billing Budgets Other topics Feature maturity Notebooks Restricted Functions JavaScript/Go SDKs BetaModal 1.0 migration guide File and project structure Developing and debugging Jupyter notebooks Asynchronous API usage Global variables Region selection GPU Metrics

Network egress billing

What is egress pricing? 

Starting October 1, 2026, Modal charges for network egress. Network egress is outbound network traffic measured from your Modal tasks. This includes traffic sent through a container’s network interface, private network traffic sent directly to other Modal containers, and uploads through Cloud Bucket Mounts. Reads from and writes to Modal Volumes do not count as network egress.

What is the pricing? 

PlanIncluded per billing cycleAdditional egress
Starter1 TiB$0.04 per GiB
Team10 TiB$0.04 per GiB
Enterprise100 TiB$0.04 per GiB

Every plan includes an egress allowance each billing cycle before charges apply. Egress beyond the included amount is billed at $0.04 per GiB.

How can I see my egress usage? 

Visit the Usage & Billing page to see your current usage. The page shows daily egress for the whole Workspace, and lets you break it down by Environment. Access to egress data through the CLI and SDK is coming soon.

Is the allowance applied separately to each Environment? 

No. The allowance applies once to total egress across the entire Workspace. Environment filters on the Usage & Billing page show how much usage occurred in a particular Environment, but they do not provide a separate allowance or an independent charge estimate. To see the estimated Workspace charge, select all Environments.

What is the timeline for these changes? 

Starting September 1, 2026, network egress usage appears live on your Usage & Billing page, including your daily egress amount and estimated charge. You are not charged for egress in September.

Starting October 1, 2026, egress is charged. Your first bill including egress arrives on November 1, 2026.

Do writes to Modal Volumes count as network egress? 

No. Reads from and writes to Modal Volumes do not count as network egress.

Transferring that data elsewhere — for example, uploading it from a Modal Function to an external API or object store — does count as egress. Reusing data stored in a Volume can avoid repeated external transfers.

How can I lower my egress usage? 

Focus on bytes your workloads send through direct network connections:

  • Compress large uploads to external APIs and object storage.
  • Remove unnecessary response fields, paginate large results, and avoid duplicate uploads or retries.
  • Cache models, datasets, or dependencies in Images or Volumes to reduce repeated downloads and startup time. Because downloads are ingress, this does not by itself reduce metered egress.
  • Cloud Bucket Mount uploads count as egress. Downloads are primarily ingress, although outbound request and protocol bytes may still be measured.
  • Keep producer and consumer logic in the same process or container when practical, so intermediate data does not cross a network interface.
  • Avoid uploading intermediate artifacts to an external service only for another Modal task to download them again.