Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 20 additions & 0 deletions docs/providers/empiriolabs.md
Original file line number Diff line number Diff line change
Expand Up @@ -144,6 +144,26 @@ curl http://localhost:4000/v1/chat/completions \
</TabItem>
</Tabs>

## Image Generation

EmpirioLabs image models work through the OpenAI-compatible route by passing the EmpirioLabs base URL and `extra_body={"sync": True}` (the EmpirioLabs image endpoint is async by default; `sync` returns the finished OpenAI-shaped response directly):

```python showLineNumbers title="EmpirioLabs Image Generation"
import os
import litellm

response = litellm.image_generation(
prompt="A glass cathedral at sunset, dramatic lighting",
model="openai/seedream-5-0-lite",
api_base="https://api.empiriolabs.ai/v1",
api_key=os.environ["EMPIRIOLABS_API_KEY"],
extra_body={"sync": True},
)
print(response.data[0].url)
```

Image model ids (for example `seedream-5-0-lite`, `wan-2-7-image`, `qwen-image-2-0`) are listed at [empiriolabs.ai/models](https://empiriolabs.ai/models).

## Additional Notes

- Thinking-capable models accept `reasoning_effort` (`none`, `low`, `medium`, `high`, `max`); the gateway maps it onto each model's native thinking controls.
Expand Down