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 AlphaEndpoints Endpoints Shared Endpoints Dedicated Endpoints Endpoint integrations Images 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 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

Endpoint integrations

Connect OpenCode, Codex, or Claude Code to your Shared Endpoints through https://inference.us-west.modal.direct. Set the request’s model to the Endpoint’s hostname, for example my-endpoint.us-west.modal.direct.

To see which Shared Endpoints a token can reach, list all model IDs with:

curl "https://inference.us-west.modal.direct/v1/models" \
  -H "Authorization: Bearer $MODAL_PROXY_TOKEN_ID.$MODAL_PROXY_TOKEN_SECRET"

OpenCode 

Install OpenCode and create a proxy token. In the OpenCode CLI, run /connect, select Modal as the provider, and enter the token as the API key in its combined form, wk-<id>.ws-<secret>. Then run /models and select your endpoint by hostname.

For CI or other headless use, set the token in the environment instead of running /connect:

export MODAL_PROXY_TOKEN="wk-<id>.ws-<secret>"

Codex 

Install Codex, create a proxy token, and define Modal as a model provider in ~/.codex/config.toml:

# ~/.codex/config.toml
[model_providers.modal]
name = "Modal"
base_url = "https://inference.us-west.modal.direct/v1"
env_key = "MODAL_PROXY_TOKEN"
wire_api = "responses"

Then you can run Codex via the following command with the endpoint hostname as the model ID:

export MODAL_PROXY_TOKEN="$MODAL_PROXY_TOKEN_ID.$MODAL_PROXY_TOKEN_SECRET"
codex \
  --model my-endpoint.us-west.modal.direct \
  --config model_provider='"modal"'

Claude Code 

Install Claude Code and create a Proxy Token. Set the token in its combined form, wk-<id>.ws-<secret>, and replace my-endpoint.us-west.modal.direct with the hostname of an Endpoint whose model supports tool calling:

export ANTHROPIC_BASE_URL="https://inference.us-west.modal.direct"
export ANTHROPIC_AUTH_TOKEN="wk-<id>.ws-<secret>"
export ANTHROPIC_MODEL="my-endpoint.us-west.modal.direct"
export ANTHROPIC_DEFAULT_FABLE_MODEL="$ANTHROPIC_MODEL"
export ANTHROPIC_DEFAULT_OPUS_MODEL="$ANTHROPIC_MODEL"
export ANTHROPIC_DEFAULT_SONNET_MODEL="$ANTHROPIC_MODEL"
export ANTHROPIC_DEFAULT_HAIKU_MODEL="$ANTHROPIC_MODEL"
claude