Skip to main content

Models

A single catalog of model IDs across the API. Use the Category column to filter to a product area, and use the Model ID exactly as shown when sending requests once that product area is live.

Categories

CategoryEndpointStatus
Image GenerationPOST /v1/images/generationsLive
Image Studio (edit)POST /v1/images/studio/editLive
ChatPOST /v1/chat/completionsLive
VideoPOST /v1/videos/...Live
AudioPOST /v1/audio/...Coming soon

Image Generation

Default model: model-dev. Endpoint: POST /v1/images/generations. common means image_width, image_height, callback_url, resolution, quality, additional_settings, and enable_fallback. Model-specific knobs are passed in additional_settings unless they are documented as top-level convenience params.
Model IDStatusDisplay nameRequired paramsOptional supported paramsCostETA
model-devLiveFlux Devprompt, modelcommon + seed, num_inference_steps, guidance_scale, output_format$0.10~15s
model-proLiveFlux Proprompt, modelcommon + seed, num_inference_steps, guidance_scale, output_format$0.10~15s
model-1.1LiveFlux Pro v1.1prompt, modelcommon + seed, output_format$0.10~15s
model-1.2LiveWan v2.2prompt, modelcommon + seed, negative_prompt, num_inference_steps, guidance_scale$0.10~30s
seedream-v4.5LiveSeedream v4.5prompt, modelcommon + seed$0.10~20s
flux-2-proLiveFlux 2 Proprompt, modelcommon + seed, output_format$0.10~20s
flux-2LiveFlux 2prompt, modelcommon + seed, num_inference_steps, guidance_scale, output_format$0.10~15s
lustify-v7LiveLustify v7prompt, modelcommon + seed, negative_prompt; max dimension 1,280 px$0.10~30s
nano-banana-pro-ultraLiveNano Banana Pro Ultraprompt, modelcommon + seed, aspect_ratio, resolution, output_format4k $0.20, 8k $0.30~20s
seedream-v5LiveSeedream v5prompt, modelcommon + seed$0.10~15s
prefect-pony-xlLivePrefect Pony XLprompt, modelcommon + seed$0.10~10s
wan-2.6LiveWan 2.6prompt, modelcommon + seed$0.10~15s
wan-2.7-text-to-imageLiveWan 2.7 Text-to-Imageprompt, modelcommon + seed$0.10~15s
wan-2.7-text-to-image-proLiveWan 2.7 Text-to-Image Proprompt, modelcommon + seed$0.10~20s
nano-banana-2LiveNano Banana 2prompt, modelcommon + seed, aspect_ratio, resolution, output_format, enable_web_search, enable_image_search1k/2k $0.10, 4k $0.20~15s
gpt-image-2LiveGPT Image 2 Text-to-Imageprompt, modelcommon + seed, aspect_ratio, resolution, quality, output_format$0.10~20s
nano-banana-proLiveNano Banana Proprompt, modelcommon + seed, aspect_ratio, resolution, output_format$0.20~20s
nano-bananaLiveNano Bananaprompt, modelcommon + seed, aspect_ratio, resolution, output_format, enable_web_search, enable_image_search$0.10~15s
gpt-imageLiveGPT Imageprompt, modelcommon + seed, aspect_ratio, resolution, quality, output_formatmedium $0.10, default/high $0.20~20s
realismLiveRealismprompt, modelcommon + negative_prompt; dimensions accepted but provider ignores exact sizing$0.10~20s
realism-2LiveRealism 2.0prompt, modelcommon + negative_prompt; dimensions accepted but provider ignores exact sizing$0.20~20s
z-image-turboLiveZ Image Turboprompt, modelcommon + negative_prompt; dimensions accepted but provider ignores exact sizing$0.20~20s

Deprecated image generation models

Model IDDisplay nameStatus
lustify-sdxlLustify SDXLDeprecated; route returns Model deprecated.

Image Studio

Edit existing images with a text instruction and one or more reference images. Default model: standard. Endpoint: POST /v1/images/studio/edit. common means callback_url, additional_settings, and enable_fallback. Model-specific knobs are passed in additional_settings.
Model IDStatusDisplay nameRequired paramsOptional supported paramsCostETA
standardLiveGemini 2.5 Flashprompt, image_urls, modelcommon; image_urls 1-5$0.10~8s
proLiveGemini 3 Proprompt, image_urls, modelcommon; image_urls 1-5$0.20~10s
qwen-image/edit-2511LiveQwen Image Edit 2511prompt, image_urls, modelcommon; image_urls 1-3$0.10~15s
Seedream-4.5-uncensoredLiveSeedream v4.5prompt, image_urls, modelcommon + seed; image_urls 1-5$0.10~15s
Wan-2.6LiveWan 2.6prompt, image_urls, modelcommon + seed, negative_prompt; image_urls 1-5$0.10~20s
Wan-2.6-image-editLiveWan 2.6 Image Editprompt, image_urls, modelcommon + seed, negative_prompt; image_urls 1-5$0.10~15s
group-editLiveQwen Group Photoprompt, image_urls, modelcommon + seed; image_urls 1-5$0.10~20s
xai/grok-imagine-image/editLiveGrok Imagine Editprompt, image_urls, modelcommon + seed; provider uses the first image$0.10~15s
seedream-v5LiveSeedream v5 Liteprompt, image_urls, modelcommon; image_urls 1-5$0.10~15s
nano-banana-2/editLiveNano Banana 2 Editprompt, image_urls, modelcommon + resolution (0.5k, 1k, 2k, 4k), aspect_ratio, output_format (png, jpeg), enable_web_search, enable_image_search; image_urls 1-50.5k/1k/2k $0.10, 4k $0.20~20s
nano-banana-2/edit-fastLiveNano Banana 2 Edit Fastprompt, image_urls, modelcommon + resolution (2k, 4k), aspect_ratio, output_format (png, jpeg); image_urls 1-5$0.10~12s
seedream-v4.5/edit-sequentialLiveSeedream v4.5 Edit Sequentialprompt, image_urls, modelcommon + seed, max_images (1-15); image_urls 1-5$0.10~25s
seedream-v5.0-lite/edit-sequentialLiveSeedream v5 Lite Edit Sequentialprompt, image_urls, modelcommon + max_images (1-15); image_urls 1-5$0.10~25s
wan-2.7-image-editLiveWan 2.7 Image Editprompt, image_urls, modelcommon + seed; image_urls 1-5$0.10~15s
wan-2.7-image-edit-proLiveWan 2.7 Image Edit Proprompt, image_urls, modelcommon + seed; image_urls 1-5$0.10~20s
gpt-image-2/editLiveGPT Image 2 Editprompt, image_urls, modelcommon + quality (low, medium, high), resolution (1k, 2k), aspect_ratio, output_format (png, jpeg, webp); image_urls 1-5low/medium $0.10, high 1k $0.30, high 2k $0.40~20s

Chat

OpenAI-compatible chat completions endpoint. Endpoint: POST /v1/chat/completions. The full list of chat model IDs and per-token pricing is loaded live on the Chat Models page, fetched directly from GET /v1/models.

Video

Default model: t2v-turbo. Endpoint: POST /v1/videos/generations. common means callback_url, additional_settings, and enable_fallback. Model-specific provider knobs such as seed, negative_prompt, and generate_audio are passed in additional_settings. generate_audio is only supported on audio-capable models (those that list it below); setting generate_audio: true adds an audio track and roughly doubles the per-second cost. The cost shown below is the default audio-off rate.
Model IDStatusDisplay nameTypeRequired paramsOptional supported paramsCostETA
t2v-turboLiveText-to-Video TurboText-to-videoprompt, modelcommon + seconds (5, 8), resolution (480p, 720p), aspect_ratio, seed, negative_prompt$0.40~43s
t2v-standardLiveText-to-Video StandardText-to-videoprompt, modelcommon + seconds, aspect_ratio (auto, 16:9, 9:16, 1:1)$1.20~63s
cosmos-predictLiveCosmos PredictText-to-videoprompt, modelcommon + seconds, aspect_ratio$0.80~90s
av-genLiveAV GenText-to-videoprompt, modelcommon + seconds (5, 10, 15), resolution (720p, 1080p)$1.00~84s
ltx-distilledLiveLTX DistilledText-to-videoprompt, modelcommon + seconds, aspect_ratio$0.3996~63s
seedance-2.0-t2vLiveSeedance 2.0 T2VText-to-videoprompt, modelcommon + seconds (5, 10, 15), resolution (480p, 720p, 1080p), aspect_ratio$1.80 default~70s
seedance-2.0-fast-t2vLiveSeedance 2.0 Fast T2VText-to-videoprompt, modelcommon + seconds (5, 10, 15), resolution (480p, 720p, 1080p), aspect_ratio$0.60 default~45s
wan-2.7-t2vLiveWan 2.7 T2VText-to-videoprompt, modelcommon + seconds (5, 10, 15), resolution (720p, 1080p), negative_prompt$1.50 default~70s
wan-2.2-ultra-fast-t2vLiveWan 2.2 Ultra-Fast T2VText-to-videoprompt, modelcommon + seconds (5, 8), resolution (480p, 720p), aspect_ratio, seed, negative_prompt$0.60 default~25s
happyhorse-1.0-t2vLiveHappyHorse 1.0 T2VText-to-videoprompt, modelcommon + seconds (3-15), resolution (720p, 1080p), aspect_ratio (16:9, 9:16, 1:1), seed$0.112-$0.224/sec~70s
i2v-turboLiveImage-to-Video TurboImage-to-videoprompt, model, image_urlcommon + seconds (5, 8), resolution (480p, 720p), aspect_ratio, seed, negative_promptabout $0.11~39s
i2v-standardLiveImage-to-Video StandardImage-to-videoprompt, model, image_urlcommon + seconds, resolution (480p, 720p), aspect_ratio (auto, 16:9, 9:16, 1:1)$0.30-$0.60~38s
i2v-proLiveImage-to-Video ProImage-to-videoprompt, model, image_urlcommon + seconds, resolution (480p, 580p, 720p), aspect_ratio (16:9, 9:16, 1:1), end_image_url$0.04-$0.08/sec~63s
i2v-soraLiveImage-to-Video SoraImage-to-videoprompt, model, image_urlcommon + seconds (4, 8, 12), aspect_ratio (16:9, 9:16, 1:1)about $0.11/sec~146s
i2v-sora-proLiveImage-to-Video Sora ProImage-to-videoprompt, model, image_urlcommon + seconds (4, 8, 12), resolution (720p, 1080p), aspect_ratio (16:9, 9:16, 1:1)$0.30-$0.50/sec~186s
wan-2.6LiveWan 2.6Image-to-videoprompt, model, image_urlcommon + seconds (5, 10, 15), resolution (720p, 1080p), negative_prompt$0.10-$0.15/sec~84s
wan-2.6-ultraLiveWan 2.6 UltraImage-to-videoprompt, model, image_urlcommon + seconds (5, 10, 15), resolution (720p, 1080p), negative_prompt$0.10-$0.15/sec~60s
wan-2.6-flashLiveWan 2.6 FlashImage-to-videoprompt, model, image_urlcommon + seconds (5, 10, 15), resolution (720p, 1080p)$0.05-$0.075/sec~45s
wan-2.2-spicyLiveWan 2.2 SpicyImage-to-videoprompt, model, image_urlcommon + seconds (5, 8), resolution (480p, 720p), seed$0.024-$0.048/sec~40s
wan-2.2-ultra-fastLiveWan 2.2 Ultra-Fast I2VImage-to-videoprompt, model, image_urlcommon + seconds (5, 8), resolution (480p, 720p), aspect_ratio, seed, negative_prompt$0.008-$0.016/sec~25s
vidu-q3-spicyLiveVidu Q3 SpicyImage-to-videoprompt, model, image_urlcommon + seconds (5, 10, 15), resolution (540p, 720p, 1080p)$0.056-$0.128/sec~60s
cosmos-predict-i2vLiveCosmos Predict I2VImage-to-videoprompt, model, image_urlcommon + seconds, aspect_ratioabout $0.50~90s
grok-imagine-videoLiveGrok Imagine VideoImage-to-videoprompt, model, image_urlcommon + seconds (6, 10), resolution (480p, 720p), aspect_ratio (2:3, 3:2, 1:1, 16:9, 9:16)about $0.04/sec~20s
sora-2LiveSora 2Smart-routed videoprompt, modelcommon + optional image_url, seconds (4, 8, 12), aspect_ratio (16:9, 9:16, 1:1)about $0.11/sec~117s
sora-2-proLiveSora 2 ProSmart-routed videoprompt, modelcommon + optional image_url, seconds (4, 8, 12), resolution (720p, 1080p), aspect_ratio (16:9, 9:16, 1:1)$0.30-$0.50/sec~169s
seedance-2.0LiveSeedance 2.0 I2VImage-to-videoprompt, model, image_urlcommon + seconds (5, 10, 15), resolution (480p, 720p, 1080p), aspect_ratio$0.12-$0.60/sec~70s
seedance-2.0-fastLiveSeedance 2.0 Fast I2VImage-to-videoprompt, model, image_urlcommon + seconds (5, 10, 15), resolution (480p, 720p, 1080p), aspect_ratio$0.10-$0.50/sec~45s
seedance-2.0-spicyLiveSeedance 2.0 Spicy I2VImage-to-videoprompt, model, image_urlcommon + seconds (5, 10, 15), resolution (480p, 720p, 1080p), aspect_ratio, generate_audio, end_image_url$0.06-$0.30/sec~70s
seedance-2.0-fast-spicyLiveSeedance 2.0 Fast Spicy I2VImage-to-videoprompt, model, image_urlcommon + seconds (5, 10, 15), resolution (480p, 720p, 1080p), aspect_ratio, generate_audio, end_image_url$0.05-$0.25/sec~45s
seedance-v1.5-pro-spicyLiveSeedance v1.5 Pro SpicyImage-to-videoprompt, model, image_urlcommon + seconds (4-12), resolution (480p, 720p, 1080p), aspect_ratio, generate_audio$0.0096-$0.0416/sec~50s
wan-2.7LiveWan 2.7 I2VImage-to-videoprompt, model, image_urlcommon + seconds (5, 10, 15), resolution (720p, 1080p), negative_prompt$0.08-$0.12/sec~70s
wan-2.7-proLiveWan 2.7 Pro I2VImage-to-videoprompt, model, image_urlcommon + seconds (5, 10, 15), resolution (1080p, 2k, 4k)$0.12-$0.16/sec~70s
wan-2.7-spicyLiveWan 2.7 Spicy I2VImage-to-videoprompt, model, image_urlcommon + seconds (5, 10, 15), resolution (720p, 1080p)$0.10-$0.15/sec~70s
grok-imagine-video-referenceLiveGrok Imagine Reference-to-VideoImage-to-videoprompt, model, image_urlcommon + optional end_image_url, seconds (6, 10), resolution (480p, 720p)about $0.04/sec~25s
happyhorse-1.0LiveHappyHorse 1.0 I2VImage-to-videoprompt, model, image_urlcommon + seconds (3-15), resolution (720p, 1080p), seed; aspect ratio follows the input image$0.112-$0.224/sec~70s
video-to-videoLiveVideo to VideoVideo-to-videoprompt, model, video_urlcommon + seconds, resolution (240p, 360p, 480p, 580p, 720p)$0.04-$0.08/sec~175s
wan-2.6-v2vLiveWan 2.6 V2VVideo-to-videoprompt, model, video_urlcommon + seconds (5, 10), resolution (720p, 1080p)$0.10-$0.15/sec~90s
wan-2.2-spicy-extendLiveWan 2.2 Spicy ExtendVideo extendprompt, model, video_urlcommon + seconds (5, 8), resolution (480p, 720p)$0.024-$0.048/sec~40s
grok-imagine-video-editLiveGrok Imagine EditVideo editprompt, model, video_urlcommon + seconds (1-8), resolution (480p, 720p)$0.06-$0.08/sec~95s
wan-2.7-video-extendLiveWan 2.7 Video ExtendVideo extendprompt, model, video_urlcommon + seconds (5, 10, 15), resolution (720p, 1080p), negative_prompt$0.08-$0.12/sec~70s
grok-imagine-video-extendLiveGrok Imagine Video ExtendVideo extendprompt, model, video_urlcommon + seconds (6, 10)about $0.04/sec~25s
happyhorse-1.0-video-editLiveHappyHorse 1.0 Video EditVideo editprompt, model, video_urlcommon + seconds (3-15), resolution (720p, 1080p), seed, reference images (up to 9, in additional_settings)$0.112-$0.224/sec~70s
happyhorse-1.0-video-extendLiveHappyHorse 1.0 Video ExtendVideo extendprompt, model, video_urlcommon + seconds (3-15), resolution (720p, 1080p), seed$0.112-$0.224/sec~70s
ultimate-video-upscalerLiveUltimate Video UpscalerVideo-to-videoprompt, model, video_urlcommon + seconds, resolution (720p, 1080p, 2k, 4k); output length follows the source clip and prompt is ignored. Billed per second of seconds — set it to your source clip’s duration (max 30)$0.016-$0.064/sec~90s
video-watermark-removerLiveVideo Watermark RemoverVideo-to-videoprompt, model, video_urlcommon + seconds; output length follows the source clip and prompt is ignored. Billed per second of seconds — set it to your source clip’s duration (max 30)$0.008/sec~90s

Audio

Audio models will be published when the audio endpoints go live. See Audio.

Variable-pricing parameters

A few models price the request based on quality or resolution. Pass these in additional_settings (or as documented per endpoint):
ParameterAccepted valuesUsed by
resolution0.5k, 1k, 2k, 4k, 8kModels marked “Variable pricing: resolution
qualitylow, medium, highModels marked “Variable pricing: quality
aspect_ratio1:1, 3:2, 2:3, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9 (plus 1:4, 4:1, 1:8, 8:1 on select models)Models that accept explicit aspect ratios
Not every model supports every value — refer to the model row for what’s accepted.