deAPI does not serve
/v1/chat/completions. Keep your existing chat connection and use deAPI for images, speech, transcription and embeddings.Prerequisites
- An Open WebUI instance and an admin account
- A deAPI API key from the deAPI Dashboard. See API Keys.
Image generation
- Open Admin Panel → Settings → Images.
- Turn on Image Generation.
- Set Image Generation Engine to Default (Open AI).
- Enter the API Base URL and API Key. Leave API Version empty.
- Type a model name into Model. The dropdown only lists OpenAI’s own models, so type the name instead.
- Set Image Size to a size the model supports, then click Save.
Open WebUI’s default size,
512x512, works on all four. It asks for b64_json, and deAPI returns a PNG. In testing, a 512x512 image from ZImageTurbo_INT8 came back in about 14 seconds.
Image editing
- On the same Images page, turn on Image Edit.
- Set Image Edit Engine to Default (Open AI).
- Enter the same API Base URL and API Key.
- Set Model to
Flux_2_Klein_4B_BF16and click Save.
Flux_2_Klein_4B_BF16 accepts the multipart image[] field that Open WebUI uses, combines up to 3 input images, and returned a 512x512 edit in about 8 seconds in testing. QwenImageEdit_Plus_NF4 (one input image) works too, but is much slower: minutes rather than seconds in testing. See Image editing for limits.
Text-to-speech
- Open Admin Panel → Settings → Audio.
- Under Text-to-Speech, set Text-to-Speech Engine to OpenAI.
- Enter the API Base URL and API Key.
- Set TTS Model to
Kokoroand TTS Voice to a Kokoro voice such asaf_nova, then click Save.
Speech-to-text
- On the same Audio page, set Speech-to-Text Engine to OpenAI.
- Enter the API Base URL and API Key.
- Set STT Model to
WhisperLargeV3Ct2and click Save.
Document embeddings
- Open Admin Panel → Settings → Documents.
- Set Embedding Model Engine to OpenAI.
- Enter the API Base URL and API Key.
- Set Embedding Model to
Bge_M3_FP16and click Save.
Bge_M3_FP16 returns 1024-dimensional vectors and handles many languages.
Troubleshooting
Next steps
OpenAI Compatibility
Every endpoint, model and field the OpenAI-compatible API supports, and where it differs from OpenAI