Emu3.5 Image is a native multimodal world model from BAAI that generates and edits images by next-token prediction over interleaved vision-language sequences, with strong text rendering and any-to-image editing.
$0.15
Daily usage of this model on NagaAI.
Share of requests served without a server error. Client errors (4xx) do not count.
Works with the OpenAI SDK pointed at our base URL. Every parameter is in the API reference.
Not enough activity data to display a chart