# Use Outrun with LiteLLM: Python SDK and Proxy

> Use the LiteLLM Python SDK or a local LiteLLM Proxy with Outrun. Copy the API base, model prefix, YAML configuration and streaming examples.

Canonical: https://outrun.to/docs/setup/litellm

Call Outrun from the LiteLLM Python SDK or a local LiteLLM Proxy.

## Before you start

Have your API key and some Outrun credit ready. Keep your key private.

[Get your API key](https://outrun.to/api-keys)

[Check balance](https://outrun.to/balance)

[Choose a model](https://outrun.to/docs/models)

**Optional setup helper Use an AI assistant to walk through these steps**

Copy the setup instructions into an AI assistant you already use. Review any file changes it suggests before allowing them.

Enter your API key directly in the app or local settings. Keep it out of the assistant’s chat.

**Connection settings Show ⌄**

Connection settings

```
api_base: https://api.outrun.to/v1
Example model: openai/claude-sonnet-5-5
API key variable: OUTRUN_API_KEY
```

Get your key from Outrun → API keys and enter it privately in the app or local settings. Test with “Reply with OK only.” Tests use credit; check Activity before retrying.

## Setup Steps

1. 1

  **Prepare your LiteLLM installation**

  Use Python 3.10 or newer with a supported LiteLLM installation. The SDK examples need the litellm package; the Proxy section also requires its proxy extra. Select a supported version before installing or upgrading.

2. 2

  **Keep your key in a local variable**

  Provide OUTRUN_API_KEY only to your local process. Use your own key from Outrun → API keys or @outrunAPI_Bot → My API key. Never put it in source control, browser code or a shared configuration.

3. 3

  **Use the OpenAI-compatible route**

  Use a model string with the openai/ prefix, and keep api_base exactly https://api.outrun.to/v1. The prefix selects LiteLLM’s OpenAI-compatible Chat Completions route; it does not change which Outrun model ID is called.

4. 4

  **Run one small request**

  Run the SDK example below once, or start the loopback-only proxy and send its example request. Requests use Outrun credit. Check Activity before repeating an interrupted request.

## Call Outrun from Python

Keep the openai/ prefix and replace the model ID with any available chat model from the model catalogue. Image, video and audio operations use their own endpoints, not this chat example.

LiteLLM Python SDK

```
import os
from litellm import completion

response = completion(
    model="openai/claude-sonnet-5-5",
    api_base="https://api.outrun.to/v1",
    api_key=os.environ["OUTRUN_API_KEY"],
    messages=[{"role": "user", "content": "Reply with OK only."}],
)
print(response.choices[0].message.content)
```

## Stream the response

Add stream=True and consume the returned chunks. Use streaming only when the selected model’s setup data supports it. The example model lists streaming support.

Streaming Python example

```
import os
from litellm import completion

response = completion(
    model="openai/claude-sonnet-5-5",
    api_base="https://api.outrun.to/v1",
    api_key=os.environ["OUTRUN_API_KEY"],
    messages=[{"role": "user", "content": "Reply with OK only."}],
    stream=True,
)
for chunk in response:
    if chunk.choices:
        print(chunk.choices[0].delta.content or "", end="", flush=True)
```

## Configure a local LiteLLM Proxy

Save this as config.yaml. model_name is the alias clients send to the local proxy; litellm_params.model is the actual Outrun model prefixed with openai/. The key stays in the proxy process environment.

| Model | Model ID | Details |
| --- | --- | --- |
| Claude Sonnet 5.5 | claude-sonnet-5-5 | Model details |
| GPT-6.1 Sol | gpt-6.1-sol | Model details |
| DeepSeek V4 Pro | deepseek-v4-pro | Model details |

Proxy config.yaml

```
model_list:
  - model_name: outrun-claude
    litellm_params:
      model: openai/claude-sonnet-5-5
      api_base: https://api.outrun.to/v1
      api_key: os.environ/OUTRUN_API_KEY
  - model_name: outrun-gpt
    litellm_params:
      model: openai/gpt-6.1-sol
      api_base: https://api.outrun.to/v1
      api_key: os.environ/OUTRUN_API_KEY
  - model_name: outrun-deepseek
    litellm_params:
      model: openai/deepseek-v4-pro
      api_base: https://api.outrun.to/v1
      api_key: os.environ/OUTRUN_API_KEY
```

## Start the proxy and call it

With the proxy extra installed and OUTRUN_API_KEY available to the process, run the command below. Keep this example bound to 127.0.0.1. The cURL model value is the configured alias, not the original Outrun ID.

Start on loopback

```
litellm --config config.yaml --host 127.0.0.1 --port 4000
```

Call the local proxy

```
curl http://127.0.0.1:4000/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model":"outrun-claude","messages":[{"role":"user","content":"Reply with OK only."}]}'
```

## Choose another model

Change only the Outrun ID after openai/ in the SDK or YAML. Use an available text/chat model with the endpoint and capabilities shown on its model page. Keep a distinct model_name for each proxy alias.

[Browse model pages](https://outrun.to/model/)[All current prices](https://outrun.to/discounted-ai-api)[API formats and endpoints](https://outrun.to/docs/api)

## If something goes wrong

**Key missing or rejected (401)**

Copy your current key from API keys. Paste it only into the app’s key field or your local key variable, then save and reopen the app.

**Not enough available credit (402)**

Check Balance and the key’s spending cap. Another request may have temporarily reserved credit; read the message before adding funds.

**Model not found (400/404)**

Copy a current model ID from Models & Pricing. A model name or a route label is not an API model ID.

**Empty replies or an interrupted request**

Check Activity first. Confirm the response-length setting is within the model’s output limit. If needed, choose another listed route or model; do not repeatedly submit the same request.

**Busy or rate limited (429)**

Wait for the active request to finish or the rate limit to reset. Avoid repeatedly submitting the same request.

[Contact @outrunsupport](https://t.me/outrunsupport)