OpenShell/docs/sandboxes/inference-routing.mdx

---
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
title: "Inference Routing"
sidebar-title: "Inference Routing"
description: "Understand and configure OpenShell inference routing through inference.local and external endpoints."
keywords: "Generative AI, Cybersecurity, Inference Routing, Configuration, Privacy, LLM, Provider"
position: 7
---

OpenShell handles inference traffic through two paths: external endpoints and `inference.local`.

| Path | How it works |
|---|---|
| External endpoints | Traffic to hosts like `api.openai.com` or `api.anthropic.com` is treated like any other outbound request, allowed or denied by `network_policies`. Refer to [Policies](/sandboxes/policies). |
| `inference.local` | A sandbox-local HTTPS endpoint that routes model requests through the gateway. The privacy router strips sandbox-supplied credentials, forwards only approved inference headers, injects the configured backend credentials, and forwards to the managed model endpoint. |

## How `inference.local` Works

When code inside a sandbox calls `https://inference.local`, the privacy router routes the request to the configured backend for that gateway. The configured model is applied to generation requests, provider credentials come from OpenShell rather than from code inside the sandbox, and only approved inference headers are forwarded upstream.

If code calls an external inference host directly, OpenShell evaluates that traffic only through `network_policies`.

| Property | Detail |
|---|---|
| Credentials | No sandbox API keys needed. Credentials come from the configured provider record. The router strips caller-supplied `Authorization` before forwarding the request. |
| Header forwarding | `inference.local` forwards only a per-provider header allowlist. OpenAI routes allow `openai-organization` and `x-model-id`. Anthropic routes allow `anthropic-version` and `anthropic-beta`. Vertex Claude rawPredict routes strip `anthropic-beta` and do not forward `anthropic-version` as a header because the router injects `anthropic_version` into the Vertex request body. NVIDIA routes allow `x-model-id`. AWS Bedrock routes have no passthrough headers today. All other caller headers are stripped. |
| Configuration | One provider and one model define sandbox inference for the active gateway. Every sandbox on that gateway sees the same `inference.local` backend. |
| Provider support | NVIDIA, Anthropic, Google Vertex AI, AWS Bedrock (via a translating bridge — direct AWS with SigV4 signing is a separate follow-up), and any OpenAI-compatible provider all work through the same endpoint. Vertex routes Claude models through `/v1/messages` and non-Anthropic models through `/v1/chat/completions`. The gateway resolves the upstream Vertex host from the provider config, including regional, global, and supported multi-region endpoints. |
| Streaming reliability | The router tolerates idle gaps of up to 120 seconds between streamed chunks so long reasoning responses are not cut off mid-stream. |
| Hot refresh | OpenShell picks up provider credential changes and inference updates without recreating sandboxes. Changes propagate within about 5 seconds by default. |

## Supported API Patterns

Supported request patterns depend on the provider configured for `inference.local`.

<Tabs>
<Tab title="OpenAI-compatible">

| Pattern | Method | Path |
|---|---|---|
| Chat Completions | `POST` | `/v1/chat/completions` |
| Completions | `POST` | `/v1/completions` |
| Responses | `POST` | `/v1/responses` |
| Embeddings | `POST` | `/v1/embeddings` |
| Model Discovery | `GET` | `/v1/models` |
| Model Discovery | `GET` | `/v1/models/*` |

</Tab>

<Tab title="Anthropic-compatible">

| Pattern | Method | Path |
|---|---|---|
| Messages | `POST` | `/v1/messages` |

</Tab>

<Tab title="AWS Bedrock">

| Pattern | Method | Path |
|---|---|---|
| InvokeModel | `POST` | `/model/{modelId}/invoke` |

The `{modelId}` segment is constrained to a single non-empty path segment to avoid path-traversal liabilities. `/model//invoke` and `/model/a/b/invoke` both no-match.

<Note>
Today the `aws-bedrock` provider type is bridge-fronted only. The router does not inject any auth header on outbound requests; the configured `BEDROCK_BASE_URL` is expected to point at a translating bridge or Bedrock-compatible proxy whose own pod holds operator-side credentials. SigV4 signing for direct AWS Bedrock is deferred to a follow-up release.

`InvokeModelWithResponseStream` is intentionally not advertised yet. The streaming path emits AWS event-stream framing, which our protocol-aware error path does not yet model; surfacing it without that work risks shipping responses the sandbox cannot interpret on failure. It will land alongside the streaming-error work in a follow-up.
</Note>

</Tab>
</Tabs>

Requests to `inference.local` that do not match the configured provider's supported patterns are denied.

Google Vertex AI does not expose every OpenAI-compatible path through `inference.local`. Vertex routes for Gemini and other non-Anthropic models currently support Chat Completions. Vertex routes for Claude models use the Anthropic Messages pattern. Base URL overrides are only supported for non-Anthropic Vertex routes.

## Configure Inference Routing

The managed local inference endpoint uses three values:

| Value | Description |
|---|---|
| Provider record | The credential backend OpenShell uses to authenticate with the upstream model host. |
| Model ID | The model to use for generation requests. |
| Timeout | Per-request timeout in seconds for upstream inference calls. Defaults to 60 seconds. |

For tested providers and base URLs, refer to [Supported Inference Providers](/sandboxes/manage-providers#supported-inference-providers).

## Create a Provider

Create a provider that holds the backend credentials you want OpenShell to use.

<Tabs>
<Tab title="NVIDIA API Catalog">

```shell
openshell provider create --name nvidia-prod --type nvidia --from-existing
```

This reads `NVIDIA_API_KEY` from your environment.

</Tab>

<Tab title="OpenAI-compatible Provider">

Any cloud provider that exposes an OpenAI-compatible API works with the `openai` provider type. You need three values from the provider: the base URL, an API key, and a model name.

```shell
openshell provider create \
    --name my-cloud-provider \
    --type openai \
    --credential OPENAI_API_KEY=<your_api_key> \
    --config OPENAI_BASE_URL=https://api.example.com/v1
```

Replace the base URL and API key with the values from your provider. For supported providers out of the box, refer to [Supported Inference Providers](/sandboxes/manage-providers#supported-inference-providers). For other providers, refer to your provider's documentation for the correct base URL, available models, and API key setup.

</Tab>

<Tab title="Google Vertex AI">

```shell
openshell provider create \
    --name vertex-local \
    --type google-vertex-ai \
    --from-gcloud-adc \
    --config VERTEX_AI_PROJECT_ID=my-gcp-project \
    --config VERTEX_AI_REGION=us-central1
```

Use [Google Vertex AI](/providers/google-vertex-ai) for the full auth flows, including the production service-account refresh path, ADC-backed providers that mint `GOOGLE_VERTEX_AI_TOKEN`, and `--from-existing` support.

</Tab>

<Tab title="Local Endpoint">

```shell
openshell provider create \
    --name my-local-model \
    --type openai \
    --credential OPENAI_API_KEY=empty-if-not-required \
    --config OPENAI_BASE_URL=http://host.openshell.internal:11434/v1
```

Use `--config OPENAI_BASE_URL` to point to any OpenAI-compatible server running where the gateway runs. For host-backed local inference, use `host.openshell.internal` or the host's LAN IP. Avoid `127.0.0.1` and `localhost`. Set `OPENAI_API_KEY` to a dummy value if the server does not require authentication.

<Tip>
For a self-contained setup, the Ollama sandbox bundles Ollama inside the sandbox itself, so no host-level provider is needed. Refer to [Inference Ollama](/get-started/tutorials/inference-ollama) for details.

</Tip>

Ollama also supports cloud-hosted models using the `:cloud` tag suffix, for example `qwen3.5:cloud`.

</Tab>

<Tab title="Anthropic">

```shell
openshell provider create --name anthropic-prod --type anthropic --from-existing
```

This reads `ANTHROPIC_API_KEY` from your environment.

</Tab>

<Tab title="AWS Bedrock">

```shell
openshell provider create \
    --name bedrock-bridge \
    --type aws-bedrock \
    --credential AWS_ACCESS_KEY_ID=unused-bridge-fronted-shape \
    --config BEDROCK_BASE_URL=http://your-bedrock-bridge.your-ns.svc.cluster.local:8080
```

Then set the inference route, passing `--no-verify` because the validation probe does not yet support Bedrock protocols:

```shell
openshell inference set \
    --provider bedrock-bridge \
    --model anthropic.claude-3-5-sonnet-20241022-v2:0 \
    --no-verify
```

**Why a placeholder credential?** `provider create` requires a non-empty `credentials` map even when the upstream auth scheme is `AuthHeader::None` — `aws-bedrock` falls into that bucket today because the router never injects a credential header on outbound requests; the bridge holds operator-side auth in its own pod. Any non-empty string value satisfies the structural requirement; `unused-bridge-fronted-shape` makes the intent obvious in `openshell provider get` output. The same pattern applies to any standalone-router profile that registers `AuthHeader::None`. When the SigV4 follow-up lands and the router begins signing requests itself, this becomes a real key.

**About the bridge-fronted shape.** The router does not inject any auth header on outbound requests. Point `BEDROCK_BASE_URL` at a translating bridge or Bedrock-compatible proxy that handles authentication in its own pod. The bridge is expected to accept Bedrock InvokeModel requests on the patterns listed above and forward to the operator's real upstream.

**About `--no-verify`.** The default validation probe does not yet recognize the `aws_bedrock_invoke` protocol, so without `--no-verify` the `inference set` call would fail before it could mint a route. The first sandbox round-trip is the real verification today.

**For direct AWS Bedrock**, refer to a future release that adds the SigV4 router-side signer. Until then, a `BEDROCK_BASE_URL` is required at provider-create time — the core profile sets `default_base_url: ""`, so route resolution rejects providers without it rather than silently forwarding prompts to AWS with no usable auth.

</Tab>
</Tabs>

## Set Inference Routing

Point `inference.local` at that provider and choose the model to use:

```shell
openshell inference set \
    --provider nvidia-prod \
    --model nvidia/nemotron-3-nano-30b-a3b
```

To override the default 60-second per-request timeout, add `--timeout`:

```shell
openshell inference set \
    --provider nvidia-prod \
    --model nvidia/nemotron-3-nano-30b-a3b \
    --timeout 300
```

The value is in seconds. When `--timeout` is omitted or set to `0`, the default of 60 seconds applies. Increase `--timeout` when you expect extended thinking phases so the full response completes before the request deadline.

## Inspect and Update the Config

Confirm that the provider and model are set correctly:

```shell
openshell inference get
Gateway inference:

  Provider: nvidia-prod
  Model: nvidia/nemotron-3-nano-30b-a3b
  Timeout: 300s
  Version: 1
```

Use `update` when you want to change only one field:

```shell
openshell inference update --model nvidia/nemotron-3-nano-30b-a3b
openshell inference update --provider openai-prod
openshell inference update --timeout 120
```

## Use the Local Endpoint from a Sandbox

After inference is configured, code inside any sandbox can call `https://inference.local` directly. The client-supplied `model` and `api_key` values are not sent upstream — the privacy router injects the real credentials from the configured provider and rewrites the model before forwarding. Some SDKs require a non-empty API key even though `inference.local` does not use the sandbox-provided value; pass any placeholder such as `unused`.

<Tabs>
<Tab title="Claude Code">

```shell
ANTHROPIC_BASE_URL="https://inference.local" ANTHROPIC_API_KEY=unused claude --bare
```

`--bare` skips the OAuth login flow and uses `ANTHROPIC_API_KEY` directly. The key is stripped by the proxy and never reaches the upstream provider.

<Note>
Claude Code appends `/v1/messages` to `ANTHROPIC_BASE_URL`, so omit the `/v1` suffix from the base URL.
</Note>

</Tab>
<Tab title="OpenCode">

```shell
ANTHROPIC_BASE_URL="https://inference.local/v1" ANTHROPIC_API_KEY=unused opencode
```

<Note>
OpenCode appends `/messages` directly to `ANTHROPIC_BASE_URL`. Include the `/v1` suffix so the full path becomes `/v1/messages`, which matches the inference pattern.
</Note>

</Tab>
<Tab title="Python (OpenAI SDK)">

```python
from openai import OpenAI

client = OpenAI(base_url="https://inference.local/v1", api_key="unused")

response = client.chat.completions.create(
    model="anything",
    messages=[{"role": "user", "content": "Hello"}],
)
```

</Tab>
<Tab title="Python (Anthropic SDK)">

```python
import anthropic

client = anthropic.Anthropic(
    base_url="https://inference.local",
    api_key="unused",
)

message = client.messages.create(
    model="anything",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}],
)
```

</Tab>
</Tabs>

Use `inference.local` when inference should stay private and credentials should not be exposed inside the sandbox. External providers reached directly belong in `network_policies` instead.

When the upstream runs on the same machine as the gateway, bind it to `0.0.0.0` and point the provider at `host.openshell.internal` or the host's LAN IP. `127.0.0.1` and `localhost` usually fail because the request originates from the gateway or sandbox runtime, not from your shell.

If the gateway runs on a remote host or behind a cloud deployment, `host.openshell.internal` points to that remote machine, not to your laptop. A locally running Ollama or vLLM process is not reachable from a remote gateway unless you add your own tunnel or shared network path.

## Verify from a Sandbox

`openshell inference set` and `openshell inference update` verify the resolved upstream endpoint by default before saving the configuration. If the endpoint is not live yet, retry with `--no-verify` to persist the route without the probe.

To confirm end-to-end connectivity from a sandbox, run:

```shell
curl https://inference.local/v1/responses \
    -H "Content-Type: application/json" \
    -d '{
      "instructions": "You are a helpful assistant.",
      "input": "Hello!"
    }'
```

A successful response confirms the privacy router can reach the configured backend and the model is serving requests.

- Gateway-scoped: Every sandbox using the active gateway sees the same `inference.local` backend.
- HTTPS only: `inference.local` is intercepted only for HTTPS traffic.
- Hot reload: Provider, model, and timeout changes are picked up by running sandboxes within about 5 seconds by default. No sandbox recreation is required.

## Next Steps

Explore related topics:

- To follow a complete Ollama-based local setup, refer to [Inference Ollama](/get-started/tutorials/inference-ollama).
- To follow a complete LM Studio-based local setup, refer to [Local Inference LM Studio](/get-started/tutorials/local-inference-lmstudio).
- To control external endpoints, refer to [Policies](/sandboxes/policies).
- To manage provider records, refer to [Providers](/sandboxes/manage-providers).