Model List

Current models cover language models, speech generation, speech recognition, multimodal understanding, image generation, and realtime interaction. model selects the capability. To pin a version, pass a snapshot model ID as model.

All Language model NewSpeech generation Speech recognition Multimodal understanding Image generation NewRealtime interaction New

Model nameDescriptionPricing 40% OFFStreaming outputAsync

nex-n2.6Latestsnapshot: nex-n2.6-2026-11-05Multimodal language model · Text, images, and video → TextPOST /v1/chat/completionsFree for a limited time0 credits✓—moss-tts-1.5-flashRecommendedsnapshot: moss-tts-1.5-flash-2026-06-26Single-speaker text-to-speech model · Text + voice_id → AudioPOST /v1/audio/speechCNY 1.20 / 10K characters24 credits / 10K characters✓✓moss-tts-1.0-prosnapshot: moss-tts-1.0-pro-2026-02-07Single-speaker text-to-speech model · Text + voice_id → AudioPOST /v1/audio/speechCNY 1.20 / 10K characters24 credits / 10K characters—✓moss-ttsd-1.0Latestsnapshot: moss-ttsd-1.0-2026-03-20Multi-speaker dialogue speech synthesis model · Text → AudioPOST /v1/audio/speech/speakersCNY 1.20 / 10K characters24 credits / 10K characters—✓moss-voice-generator-1.0Latestsnapshot: moss-voice-generator-1.0-2026-07-22Generate speech from text and voice instructions · Text + instruction → AudioPOST /v1/audio/voice/generationsCNY 1.20 / 10K characters24 credits / 10K characters—✓moss-transcribe-1.0Latestsnapshot: moss-transcribe-1.0-2026-07-22Standard audio transcription model · Audio → TextPOST /v1/audio/transcriptionsCNY 0.48 / hour9.60 credits / hour—✓moss-transcribe-diarize-proRecommendedsnapshot: moss-transcribe-diarize-pro-2026-07-03Multi-speaker transcription model, supports audio up to 60 minutes · Audio → TextPOST /v1/audio/transcriptionsCNY 1.20 / hour24 credits / hour✓✓moss-vl-1.0Betasnapshot: moss-vl-1.0-2026-07-08Multimodal understanding model, Beta · Text instructions + image/video → TextPOST /v1/responsesFree for a limited time0 credits——moss-vl-realtime-1.0Betasnapshot: moss-vl-realtime-1.0-2026-09-09Realtime video understanding model, Beta · Continuous image frames + text → Incremental textWebSocket /v1/realtimeFree for a limited time0 credits✓—moss-image-base-1.0Betasnapshot: moss-image-base-1.0-2026-10-09Text-to-image model with long-text, layout generation and text rendering support · Text → ImagePOST /v1/images/generationsLow resolution · CNY 0.12 / imageAbout 1 MP · 2.40 credits / imageHigh resolution · CNY 0.18 / imageAbout 2 MP · 3.60 credits / image——moss-image-sft-1.0Betasnapshot: moss-image-sft-1.0-2026-10-09Text-to-image model, fine-tuned version, with long-text, layout generation and text rendering support · Text → ImagePOST /v1/images/generationsLow resolution · CNY 0.12 / imageAbout 1 MP · 2.40 credits / imageHigh resolution · CNY 0.18 / imageAbout 2 MP · 3.60 credits / image——moss-live-1.0Betasnapshot: moss-live-1.0-2026-11-02Realtime interaction model, Beta · Realtime audio + realtime video stream → Audio + textWebSocket /v1/realtimeFree for a limited time0 credits✓✓