# Use LiteLLM with Bridge

URL: https://bridge.wekoya.tech/guides/litellm
Updated: 2026-11-08

**In short:** In LiteLLM, prefix the Bridge model ID with `openai/` and set `api_base` to Bridge's API, including `/v1`, with your Bridge key. That works in the Python SDK and in the proxy's config.yaml, so every Bridge model is reachable through LiteLLM, billed in naira.

## Python SDK

```python
import os, litellm

reply = litellm.completion(
    model="openai/gemini-3.5-flash-lite",
    api_base="https://wekoya-api.wekoya.tech/v1",
    api_key=os.environ["WEKOYA_API_KEY"],
    messages=[{"role": "user", "content": "Hello"}],
)
```

## Proxy config.yaml

```yaml
model_list:
  - model_name: claude-sonnet
    litellm_params:
      model: openai/claude-sonnet-5-5
      api_base: https://wekoya-api.wekoya.tech/v1
      api_key: os.environ/WEKOYA_API_KEY
```

`api_base` must end in `/v1` and nothing after it; LiteLLM adds the rest. Without `/v1`, requests fail with Not Found.

[Create a free account](https://bridge.wekoya.tech/sign-up)

## Common questions

**Why the openai/ prefix?**

It tells LiteLLM to call an OpenAI-compatible Chat Completions endpoint, which is what Bridge serves.

## Read next

- [Aider with Bridge](https://bridge.wekoya.tech/guides/aider)
- [OpenRouter alternatives](https://bridge.wekoya.tech/guides/openrouter-alternatives-africa)