> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tensormesh.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Auth And Config

> Understand Tensormesh SDK auth, environment variables, and the difference between serverless and control-plane usage.

The SDK keeps auth and routing explicit. It does not read CLI config files by default.

The public inference surface exposes `chat.completions`, `models`, `completions`, `responses`, `tokenize`, `detokenize`, `health`, and `version`.

The SDK resolves configuration in this order:

1. constructor arguments
2. environment variables
3. built-in defaults

## Surface Boundaries

* **Control Plane**
  * auth: bearer token
  * client namespace: `client.control_plane`
* **Serverless inference**
  * auth: inference API key for POST routes; the default public host also serves `models`, `health`, and `version` without one
  * client namespace: `client.inference.serverless`
  * extra namespaces: `models`, `completions`, `responses`, `tokenize`, `detokenize`, `health`, and `version`
  * model value: serverless model name

## Get Credentials

* For a Control Plane bearer token, use [CLI Authentication](/cli/guides/authentication). The CLI browser flow stores the token locally, and `tm auth print-token --yes-i-know` can print it for a controlled SDK setup when you need it outside the CLI.
* For an inference API key, either use the key your Tensormesh environment already issued to you, or create one through the authenticated workflow:

```sh theme={null}
tm auth login
USER_ID="$(tm --output json auth whoami | python3 -c 'import json,sys; print(json.load(sys.stdin)["user"]["id"])')"
tm users api-keys create --user-id "$USER_ID" --name sdk-key --yes
```

If your environment does not expose self-serve API key creation, ask your operator or admin for the exact inference API key to use.

* If you only have inference credentials, you can still use the serverless SDK surface without Control Plane login.

If you are coming from the CLI-managed flow, `gateway_api_key` in `config.toml` is the stored inference API key used by the SDK as `inference_api_key`.

## Environment Variables

The SDK supports these environment variables:

* `TENSORMESH_CONTROL_PLANE_TOKEN`
* `TENSORMESH_CONTROL_PLANE_BASE_URL`
* `TENSORMESH_INFERENCE_API_KEY`
* `TENSORMESH_SERVERLESS_BASE_URL`
* `TENSORMESH_TIMEOUT_SECONDS`
* `TENSORMESH_MAX_RETRIES`
* `TENSORMESH_CA_BUNDLE`

Blank environment-variable values are treated as unset. Explicit constructor
arguments still need to be valid non-empty values.

## Constructor-Based Configuration

```python theme={null}
from tensormesh import Tensormesh

client = Tensormesh(
    control_plane_token="YOUR_CONTROL_PLANE_TOKEN",
    inference_api_key="YOUR_INFERENCE_API_KEY",
    timeout=30,
    max_retries=2,
)
```

`max_retries` applies to idempotent HTTP methods. The main inference calls on this SDK surface are POST requests such as `/v1/chat/completions`, `/v1/completions`, `/v1/responses`, `/tokenize`, and `/detokenize`, so those requests are not retried automatically.

## Environment-Based Configuration

```sh theme={null}
export TENSORMESH_CONTROL_PLANE_TOKEN="YOUR_CONTROL_PLANE_TOKEN"
export TENSORMESH_INFERENCE_API_KEY="YOUR_INFERENCE_API_KEY"
```

```python theme={null}
from tensormesh import Tensormesh

client = Tensormesh()
```

## When To Use CLI Login

The SDK does not require `tm auth login`.

* **Production deployments and CI environments**: supply credentials through environment variables (`TENSORMESH_INFERENCE_API_KEY`, `TENSORMESH_CONTROL_PLANE_TOKEN`, etc.). No browser interaction is required.
* **Local development**: use `tm auth login` for the browser-based Control Plane auth flow when you want the CLI to store and manage the token locally.

## Common Mistakes

* trying to use a control-plane bearer token for inference
* assuming the SDK reads `~/.config/tensormesh/` automatically

## Related Guides

* [Getting Started](/sdk/guides/getting-started)
* [Inference](/sdk/guides/inference)
* [Control Plane](/sdk/guides/control-plane)