Multimodal
Multimodal capabilities depend on the selected model. Confirm currently available multimodal models via GET /v1/models or the console pricing page.
Images
OpenAI-style image generation:
LLMoxy also forwards model-specific image parameters as long as the selected model supports them.
Image editing routes:
POST /v1/images/edits
POST /v1/editsAudio
Text-to-speech:
Audio transcription and translation use multipart form upload:
POST /v1/audio/transcriptions
POST /v1/audio/translationsVideo
OpenAI-compatible video generation:
Query status:
Download content:
LLMoxy also supports the POST /v1/video/generations JSON video generation interface, as well as vendor-style routes such as Kling and Jimeng. See the console model list for specific supported models.
Realtime
Realtime uses a WebSocket endpoint:
wss://llmoxy.com/v1/realtime?model=gpt-4o-realtime-previewServer-side clients can use standard auth headers during the handshake; browser clients can use the OpenAI-style subprotocol key format.
