Overview - BizyAir Docs

Model Launch

The following model APIs are now available on BizyAir. You can call the models below via the Model API; details are as follows:Model API names:

gpt-image-2-6-flare-official/text-to-image
gpt-image-2-6-flare-official/image-to-image
gpt-image-2-6-sunburst-official/text-to-image
gpt-image-2-6-sunburst-official/image-to-image
heygen-1-0-official/text-to-video
heygen-1-0-official/image-to-video
heygen-1-0-official/reference-to-video
kling-4-0-official/text-to-video
kling-4-0-official/flf-to-video
kling-4-0-official/reference-to-video
kling-4-0-flash-official/text-to-video
kling-4-0-flash-official/image-to-video
kling-4-0-flash-official/reference-to-video
kling-4-0-flash-official/video-edit
gemini-omni-flash-1-2-official/text-to-video
gemini-omni-flash-1-2-official/flf-to-video
gemini-omni-flash-1-2-official/reference-to-video
gemini-omni-flash-1-2-official/video-edit
gemini-omni-flash-1-2-official/video-extend
gemini-omni-flash-1-2-official/video-upscaler
minimax-h3-max-official/text-to-video
minimax-h3-max-official/flf-to-video
minimax-h3-max-official/reference-to-video
minimax-h3-max-official/video-extend
minimax-h3-max-official/insert-video
minimax-h3-max-official/lip-sync
minimax-h3-max-official/recast
minimax-h3-max-official/reframe-video
minimax-h3-max-official/relight
minimax-h3-max-turbo-official/text-to-video
minimax-h3-max-turbo-official/flf-to-video
minimax-h3-max-turbo-official/video-extend
kling-create-voice-official/audio-tools/audio-to-audio
minimax-voice-clone-official/audio-to-audio

ComfyUI node names:

GPT Image 2.6 Flare Text to Image (Official)
GPT Image 2.6 Flare Image to Image (Official)
GPT Image 2.6 Sunburst Text to Image (Official)
GPT Image 2.6 Sunburst Image to Image (Official)
HeyGen Video Text to Video (Official)
HeyGen Video Image to Video (Official)
HeyGen Video Reference to Video (Official)
Kwaivgi Kling 4.0 Text To Video (Official)
Kwaivgi Kling 4.0 FLF To Video (Official)
Kwaivgi Kling 4.0 Reference To Video (Official)
Kling 4.0 Flash Text to Video (Official)
Kling 4.0 Flash Image to Video (Official)
Kling 4.0 Flash Reference to Video (Official)
Kling 4.0 Flash Video Edit (Official)
Google Gemini Omni Flash 1.2 Text to Video (Official)
Google Gemini Omni Flash 1.2 FLF to Video (Official)
Google Gemini Omni Flash 1.2 Reference to Video (Official)
Google Gemini Omni Flash 1.2 Video Edit (Official)
Google Gemini Omni Flash 1.2 Video Extend (Official)
Google Gemini Omni Flash 1.2 Video Upscale (Official)
MiniMax H3 Max Text to Video (Official)
MiniMax H3 Max FLF to Video (Official)
MiniMax H3 Max Reference to Video (Official)
MiniMax H3 Max Video Extend (Official)
MiniMax H3 Max Insert Video (Official)
MiniMax H3 Max Lip Sync (Official)
MiniMax H3 Max Recast (Official)
MiniMax H3 Max Reframe Video (Official)
MiniMax H3 Max Relight (Official)
MiniMax H3 Max Turbo Text to Video (Official)
MiniMax H3 Max Turbo FLF to Video (Official)
MiniMax H3 Max Turbo Video Extend (Official)
Kwaivgi Kling Create Voice (Official)
MiniMax Voice Cloning (Official)

See the Model APIs for details.

Platform Service Adjustment

Model Pricing AdjustmentsTo continue providing stable model services, BizyAir is adjusting the pricing of the following model APIs, effective November 3, 2026 (UTC+8). All prices are in USD:

nano-banana-2-official/text-to-image
nano-banana-2-official/image-to-image
- 0.5K: $0.04/image → $0.09/image.
- 1K: $0.06/image → $0.11/image.
- 2K: $0.08/image → $0.17/image.
- 4K: $0.11/image → $0.21/image.
nano-banana-pro-official/text-to-image
nano-banana-pro-official/image-to-image
- 1K: $0.10/image → $0.20/image.
- 2K: $0.12/image → $0.20/image.
- 4K: $0.18/image → $0.37/image.

Additional charges (per call):

Web search: $0.015/call, applicable to all model APIs above.
High thinking level: $0.002/call, applicable to nano-banana-2-official/text-to-image and nano-banana-2-official/image-to-image.

See the pricing page for details. If you have any questions, please contact contact@bizyair.ai.

Model Launch

The following model APIs are now available on BizyAir. You can call the models below via the Model API; details are as follows:Model API names:

bizyair/glm-tts/text-to-speech
bizyair/voxcpm-2/text-to-speech
bizyair/moss-tts-1-5/text-to-speech
bizyair/dots-tts/text-to-speech
bizyair/moss-image-turbo-with-lora/text-to-image
bizyair/moss-image-quality-with-lora/text-to-image
wan-3-0-prime-official/text-to-video
wan-3-0-prime-official/flf-to-video
wan-3-0-prime-official/reference-to-video

ComfyUI node names:

BizyAir GLM TTS Text To Speech
BizyAir VoxCPM 2 Text To Speech
BizyAir MOSS TTS 1.5 Text To Speech
BizyAir Dots TTS Text To Speech
BizyAir MOSS Image Turbo with LoRA Text to Image
BizyAir MOSS Image Quality with LoRA Text to Image
Alibaba Wan 3.0 Prime Text to Video (Official)
Alibaba Wan 3.0 Prime FLF to Video (Official)
Alibaba Wan 3.0 Prime Reference to Video (Official)

See the Model APIs for details.

Platform Service Adjustment

Tiers and Rate LimitsTo improve the third-party model service experience for higher-tier members, BizyAir is adjusting the rate limits for third-party model APIs as follows, effective October 27, 2026 (UTC+8):

RPD / RPH limit increase for Iron tier and above on third-party models:
- Old: RPD and RPH limits for Iron through Platinum tiers were relatively low with small gaps between tiers.
- New: RPD and RPH for Iron, Bronze, Silver, Gold, and Platinum tiers are significantly increased; RPM remains unchanged. Specific adjustments:
  - Iron: RPD increased from 120 to 300, RPH increased from 60 to 120
  - Bronze: RPD increased from 300 to 1000, RPH increased from 100 to 200
  - Silver: RPD increased from 500 to 2500, RPH increased from 150 to 500
  - Gold: RPD increased from 1000 to 5000, RPH increased from 300 to 1000
  - Platinum: RPD increased from 3000 to 7200, RPH increased from 600 to 2000
Self-hosted Model API Rate Limits:
- Old: RPD / RPH / RPM limits for each membership tier followed the documented standards.
- New: No changes to any tier limits.

Rate limits for the Basic tier on third-party models and for all tiers on self-hosted models remain unchanged.

See tiers and rate limits for details. If you have any questions, please contact contact@bizyair.ai.

Model Launch

The following model APIs are now available on BizyAir. You can call the models below via the Model API; details are as follows:Model API names:

gemini-4-0-official/large-language-models
gemini-4-0-official/vision
yinchaoyongxian-official/text-to-audio/song-generation
yinchaoyongxian-official/audio-to-audio/song-reference
yinchaoyongxian-official/audio-to-audio/bgm-generation
pixverse-v6-official/text-to-video
pixverse-v6-official/image-to-video
pixverse-v6-official/flf-to-video
pixverse-v6-official/video-extend
ltx-2-5-fast-official/text-to-video
ltx-2-5-fast-official/flf-to-video
ltx-2-5-pro-official/text-to-video
ltx-2-5-pro-official/flf-to-video
flux-3-klein-official/text-to-image
flux-3-klein-official/image-to-image

ComfyUI node names:

Google Gemini 4.0 Argon (Official)
Google Gemini 4.0 Argon Vision (Official)
Yinchaoyongxian Song Generation (Official)
Yinchaoyongxian Reference Song Generation (Official)
Yinchaoyongxian BGM Generation (Official)
PixVerse V6 Text to Video (Official)
PixVerse V6 Image to Video (Official)
PixVerse V6 FLF to Video (Official)
PixVerse V6 Video Extend (Official)
Lightricks LTX 2.5 Fast Text to Video (Official)
Lightricks LTX 2.5 Fast FLF to Video (Official)
Lightricks LTX 2.5 Pro Text to Video (Official)
Lightricks LTX 2.5 Pro FLF to Video (Official)
FLUX.3 Klein Text to Image (Official)
FLUX.3 Klein Image to Image (Official)

See the Model APIs for details.

Platform Service Adjustment

Model Pricing AdjustmentsTo continue providing stable model services, BizyAir is adjusting the pricing of the following model APIs, effective November 4, 2026 (UTC+8). All prices are in USD:

gpt-image-2-5-flare-channel/text-to-image
gpt-image-2-5-flare-channel/image-to-image
gpt-image-2-5-sunburst-channel/text-to-image
gpt-image-2-5-sunburst-channel/image-to-image
- 1K / 2K / 4K: $0.03/call → $0.06/call (flat per call, same price across resolutions).

See the pricing page for details. If you have any questions, please contact contact@bizyair.ai.

Model Launch

The following model APIs are now available on BizyAir. You can call the models below via the Model API; details are as follows:Model API names:

vidu-q4-official/image-to-video
vidu-q4-official/reference-to-video

ComfyUI node names:

Vidu Q4 Image to Video (Official)
Vidu Q4 Reference to Video (Official)

See the Model APIs for details.

Model Launch

The following model APIs are now available on BizyAir. You can call the models below via the Model API; details are as follows:Model API names:

nano-banana-2-1-official/text-to-image
nano-banana-2-1-official/image-to-image
nano-banana-2-1-channel/text-to-image
nano-banana-2-1-channel/image-to-image
flux-3-official/text-to-image
flux-3-official/image-to-image
qwen-image-2-1-official/text-to-image
qwen-image-2-1-official/image-to-image
bizyair/video-upscaler
bizyair/video-fps-increaser/video-tools/fps-increaser
bizyair/depth-anything-v3/image-tools/depth
bizyair/depth-anything-v3/video-tools/depth
bizyair/image-tools/watermark-remover
bizyair/qwen-image/image-to-image/layer-decomposition
bizyair/image-tools/background-remover
bizyair/image-tools/eraser
bizyair/image-tools/outpaint
bizyair/flux-klein/image-tools/watermark-remover
bria-expand-official/image-tools/outpaint
topaz-upscale-image-precision-official/image-to-image
flux-3-official/text-to-video
flux-3-official/image-to-video
flux-3-official/flf-to-video
flux-3-official/video-extend
gemini-3-8-flash-official/large-language-models
gemini-3-8-flash-official/vision
minimax-music-official/text-to-audio
seedance-2-5-official/text-to-video
seedance-2-5-official/flf-to-video
seedance-2-5-official/reference-to-video
seedance-2-5-us-official/text-to-video
seedance-2-5-us-official/flf-to-video
seedance-2-5-us-official/reference-to-video
minimax-h3-lora-channel/text-to-video
minimax-h3-lora-channel/flf-to-video
minimax-h3-lora-channel/reference-to-video
bytedance/video-upscaler
gemini-omni-flash-1-1-official/text-to-video
gemini-omni-flash-1-1-official/flf-to-video
gemini-omni-flash-1-1-official/reference-to-video
gemini-omni-flash-1-1-official/video-edit
dreamactor-2-official/reference-to-video
bizyair/qwen-image/image-to-image/edit-multiple-angles
seedream-5-0-flash-official/text-to-image
seedream-5-0-flash-official/image-to-image/edit
seedream-5-0-flash-official/image-to-image/layer-decomposition

ComfyUI node names:

Google Nano Banana 2.1 Text to Image (Official)
Google Nano Banana 2.1 Image to Image (Official)
Google Nano Banana 2.1 Text to Image (Economy)
Google Nano Banana 2.1 Image to Image (Economy)
FLUX 3 Text to Image (Official)
FLUX 3 Image to Image Edit (Official)
Alibaba Qwen Image 2.1 Text to Image (Official)
Alibaba Qwen Image 2.1 Image to Image (Official)
BizyAir Video Upscaler
BizyAir Video FPS Increaser
BizyAir Depth Anything V3 Image
BizyAir Depth Anything V3 Video
BizyAir Watermark Remover
BizyAir Qwen Image Layered
BizyAir Background Remover
BizyAir Eraser
BizyAir Outpaint
BizyAir Flux Klein Watermark Remover
Bria Expand (Official)
Topaz Upscale Image Precision (Official)
FLUX 3 Text to Video (Official)
FLUX 3 Image to Video (Official)
FLUX 3 FLF to Video (Official)
FLUX 3 Video Extend (Official)
Google Gemini 3.8 Flash (Official)
Google Gemini 3.8 Flash Vision (Official)
MiniMax Music (Official)
ByteDance Seedance 2.5 Text to Video (Official)
ByteDance Seedance 2.5 FLF to Video (Official)
ByteDance Seedance 2.5 Reference to Video (Official)
ByteDance Seedance 2.5 US Text to Video (Official)
ByteDance Seedance 2.5 US FLF to Video (Official)
ByteDance Seedance 2.5 US Reference to Video (Official)
MiniMax H3 with LoRA Text to Video (Economy)
MiniMax H3 with LoRA FLF to Video (Economy)
MiniMax H3 with LoRA Reference to Video (Economy)
ByteDance Video Upscaler (Official)
Gemini Omni Flash 1.1 Text to Video (Official)
Gemini Omni Flash 1.1 FLF to Video (Official)
Gemini Omni Flash 1.1 Reference to Video (Official)
Gemini Omni Flash 1.1 Video Edit (Official)
ByteDance DreamActor 2 Motion Control (Official)
BizyAir Qwen Image Edit Multiple Angles
ByteDance Seedream 5.0 Flash Text to Image (Official)
ByteDance Seedream 5.0 Flash Image to Image Edit (Official)
ByteDance Seedream 5.0 Flash Image to Image Layer Decomposition (Official)

See the Model APIs for details.

Model Launch

The following model APIs are now available on BizyAir. You can call the models below via the Model API; details are as follows:Model API names:

gpt-image-2-5-flare-official/text-to-image
gpt-image-2-5-flare-official/image-to-image
gpt-image-2-5-sunburst-official/text-to-image
gpt-image-2-5-sunburst-official/image-to-image
gpt-image-2-5-flare-channel/text-to-image
gpt-image-2-5-flare-channel/image-to-image
gpt-image-2-5-sunburst-channel/text-to-image
gpt-image-2-5-sunburst-channel/image-to-image

ComfyUI node names:

GPT Image 2.5 Flare Text to Image (Official)
GPT Image 2.5 Flare Image to Image (Official)
GPT Image 2.5 Sunburst Text to Image (Official)
GPT Image 2.5 Sunburst Image to Image (Official)
GPT Image 2.5 Flare Text to Image (Economy)
GPT Image 2.5 Flare Image to Image (Economy)
GPT Image 2.5 Sunburst Text to Image (Economy)
GPT Image 2.5 Sunburst Image to Image (Economy)

See the Model APIs for details.

Model Launch

The following model APIs are now available on BizyAir. You can call the models below via the Model API; details are as follows:Model API names:

seedream-5-0-pro-official/text-to-image
seedream-5-0-pro-official/image-to-image/edit
seedream-5-0-pro-official/image-to-image/layer-decomposition
qwen-image-3-0-pro-official/text-to-image
qwen-image-3-0-pro-official/image-to-image
qwen-image-3-0-official/text-to-image
qwen-image-3-0-official/image-to-image
seedance-2-5-official/text-to-video
seedance-2-5-official/flf-to-video
seedance-2-5-official/reference-to-video
seedance-2-5-official/video-edit
seedance-2-5-official/video-extend
happy-horse-1-1-official/text-to-video
happy-horse-1-1-official/image-to-video
happy-horse-1-1-official/reference-to-video
wan-3-0-official/text-to-video
wan-3-0-official/flf-to-video
wan-3-0-official/reference-to-video
minimax-h3-official/text-to-video
minimax-h3-official/flf-to-video
minimax-h3-official/reference-to-video
minimax-h3-channel/text-to-video
minimax-h3-channel/flf-to-video
minimax-h3-channel/reference-to-video
seedance-2-0-mini-official/text-to-video
seedance-2-0-mini-official/flf-to-video
seedance-2-0-mini-official/reference-to-video
seedance-2-0-official/text-to-video
seedance-2-0-official/flf-to-video
seedance-2-0-official/reference-to-video
grok-imagine-image-2-0-official/text-to-image
grok-imagine-image-2-0-official/image-to-image
gemini-3-7-flash-official/large-language-models
gemini-3-7-flash-official/vision

ComfyUI node names:

ByteDance Seedream 5.0 Pro Text to Image (Official)
ByteDance Seedream 5.0 Pro Image to Image Edit (Official)
ByteDance Seedream 5.0 Pro Layer Decomposition (Official)
Alibaba Qwen Image 3.0 Pro Text to Image (Official)
Alibaba Qwen Image 3.0 Pro Image to Image (Official)
Alibaba Qwen Image 3.0 Text to Image (Official)
Alibaba Qwen Image 3.0 Image to Image (Official)
ByteDance Seedance 2.5 Text to Video (Official)
ByteDance Seedance 2.5 FLF to Video (Official)
ByteDance Seedance 2.5 Reference to Video (Official)
ByteDance Seedance 2.5 Video Edit (Official)
ByteDance Seedance 2.5 Video Extend (Official)
Alibaba Happy Horse 1.1 Text to Video (Official)
Alibaba Happy Horse 1.1 Image to Video (Official)
Alibaba Happy Horse 1.1 Reference to Video (Official)
Alibaba Wan 3.0 Text to Video (Official)
Alibaba Wan 3.0 FLF to Video (Official)
Alibaba Wan 3.0 Reference to Video (Official)
MiniMax H3 Text to Video (Official)
MiniMax H3 FLF to Video (Official)
MiniMax H3 Reference to Video (Official)
MiniMax H3 Text to Video (Economy)
MiniMax H3 FLF to Video (Economy)
MiniMax H3 Reference to Video (Economy)
ByteDance Seedance 2.0 Mini Text to Video (Official)
ByteDance Seedance 2.0 Mini FLF to Video (Official)
ByteDance Seedance 2.0 Mini Reference to Video (Official)
ByteDance Seedance 2.0 Text to Video (Official)
ByteDance Seedance 2.0 FLF to Video (Official)
ByteDance Seedance 2.0 Reference to Video (Official)
xAI Grok Imagine Image 2.0 Text to Image (Official)
xAI Grok Imagine Image 2.0 Image to Image (Official)
Google Gemini 3.7 Flash (Official)
Google Gemini 3.7 Flash Vision (Official)

See the Model APIs for details.

Model Deprecation Notice

To further optimize resource allocation and provide more advanced and reliable services, BizyAir will deprecate the following models:Model API names:

grok-image-channel/image-to-image
grok-image-channel/text-to-image

ComfyUI node names:

xAI Grok Image Image To Image (Economy)
xAI Grok Image Text To Image (Economy)

If you are using any of the above models, please switch to another model or replace the node as soon as possible to avoid service interruption.

​Model Launch

​Platform Service Adjustment

​Model Launch

​Platform Service Adjustment

​Model Launch

​Platform Service Adjustment

​Model Launch

​Model Launch

​Model Launch

​Model Launch

​Model Deprecation Notice

Model Launch

Platform Service Adjustment

Model Launch

Platform Service Adjustment

Model Launch

Platform Service Adjustment

Model Launch

Model Launch

Model Launch

Model Launch

Model Deprecation Notice