image/text_to_image
Start from 1 credit
ready
Omni Image AIO
omni / omni-image-aio
Production image generation and editing runtime for text, single-image, and dual-image workflows.
text_to_imageimage_edit
在 Playground 打开模型
浏览 Omni API 模型组，并直接进入 Playground 操作。
video/text_to_video
Start from 6 credits
ready
Omni Video AIO
omni / omni-video-aio
Video generation and transformation runtime for text, image, first-last-frame, and video-to-video jobs.
text_to_videoimage_to_videovideo_to_video
在 Playground 打开
multi/image_upscale
Start from 1 credit
ready
Omni Multi AIO
omni / omni-multi-aio
One 5090-backed mixed runtime for image upscaling, audio transcription, voice-clone TTS, multimodal chat, and talk-to-prompt.
image_upscaleaudio_transcribevoice_clone_ttsvlm_chattalk2prompt
在 Playground 打开audio/speech_to_text
Audio-minute and character pricing planned
planned
Speech Toolkit Preview
omni / speech-toolkit-preview
Forward-compatible speech workflows for STT, translation, TTS, voice clone, and voice conversion.
stttranslationttsvoice_clonevoice_conversion
在 Playground 打开text/text_generation
Token pricing planned
planned
Text Generation Preview
omni / text-generation-preview
Forward-compatible text generation and chat schema for OmniVllm-style workers.
text_generationllm_chat
在 Playground 打开realtime/realtime_voice_session
Session-minute pricing planned
planned
Realtime Voice Preview
omni / realtime-voice-agent
Realtime voice model group reserved for low-latency session workloads.
realtime_voice
在 Playground 打开