Models
A single catalog of model IDs across the API. Use theCategory 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
| Category | Endpoint | Status |
|---|---|---|
| Image Generation | POST /v1/images/generations | Live |
| Image Studio (edit) | POST /v1/images/studio/edit | Live |
| Chat | POST /v1/chat/completions | Live |
| Video | POST /v1/videos/... | Live |
| Audio | POST /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 ID | Status | Display name | Required params | Optional supported params | Cost | ETA |
|---|---|---|---|---|---|---|
model-dev | Live | Flux Dev | prompt, model | common + seed, num_inference_steps, guidance_scale, output_format | $0.10 | ~15s |
model-pro | Live | Flux Pro | prompt, model | common + seed, num_inference_steps, guidance_scale, output_format | $0.10 | ~15s |
model-1.1 | Live | Flux Pro v1.1 | prompt, model | common + seed, output_format | $0.10 | ~15s |
model-1.2 | Live | Wan v2.2 | prompt, model | common + seed, negative_prompt, num_inference_steps, guidance_scale | $0.10 | ~30s |
seedream-v4.5 | Live | Seedream v4.5 | prompt, model | common + seed | $0.10 | ~20s |
flux-2-pro | Live | Flux 2 Pro | prompt, model | common + seed, output_format | $0.10 | ~20s |
flux-2 | Live | Flux 2 | prompt, model | common + seed, num_inference_steps, guidance_scale, output_format | $0.10 | ~15s |
lustify-v7 | Live | Lustify v7 | prompt, model | common + seed, negative_prompt; max dimension 1,280 px | $0.10 | ~30s |
nano-banana-pro-ultra | Live | Nano Banana Pro Ultra | prompt, model | common + seed, aspect_ratio, resolution, output_format | 4k $0.20, 8k $0.30 | ~20s |
seedream-v5 | Live | Seedream v5 | prompt, model | common + seed | $0.10 | ~15s |
prefect-pony-xl | Live | Prefect Pony XL | prompt, model | common + seed | $0.10 | ~10s |
wan-2.6 | Live | Wan 2.6 | prompt, model | common + seed | $0.10 | ~15s |
wan-2.7-text-to-image | Live | Wan 2.7 Text-to-Image | prompt, model | common + seed | $0.10 | ~15s |
wan-2.7-text-to-image-pro | Live | Wan 2.7 Text-to-Image Pro | prompt, model | common + seed | $0.10 | ~20s |
nano-banana-2 | Live | Nano Banana 2 | prompt, model | common + seed, aspect_ratio, resolution, output_format, enable_web_search, enable_image_search | 1k/2k $0.10, 4k $0.20 | ~15s |
gpt-image-2 | Live | GPT Image 2 Text-to-Image | prompt, model | common + seed, aspect_ratio, resolution, quality, output_format | $0.10 | ~20s |
nano-banana-pro | Live | Nano Banana Pro | prompt, model | common + seed, aspect_ratio, resolution, output_format | $0.20 | ~20s |
nano-banana | Live | Nano Banana | prompt, model | common + seed, aspect_ratio, resolution, output_format, enable_web_search, enable_image_search | $0.10 | ~15s |
gpt-image | Live | GPT Image | prompt, model | common + seed, aspect_ratio, resolution, quality, output_format | medium $0.10, default/high $0.20 | ~20s |
realism | Live | Realism | prompt, model | common + negative_prompt; dimensions accepted but provider ignores exact sizing | $0.10 | ~20s |
realism-2 | Live | Realism 2.0 | prompt, model | common + negative_prompt; dimensions accepted but provider ignores exact sizing | $0.20 | ~20s |
z-image-turbo | Live | Z Image Turbo | prompt, model | common + negative_prompt; dimensions accepted but provider ignores exact sizing | $0.20 | ~20s |
Deprecated image generation models
| Model ID | Display name | Status |
|---|---|---|
lustify-sdxl | Lustify SDXL | Deprecated; 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 ID | Status | Display name | Required params | Optional supported params | Cost | ETA |
|---|---|---|---|---|---|---|
standard | Live | Gemini 2.5 Flash | prompt, image_urls, model | common; image_urls 1-5 | $0.10 | ~8s |
pro | Live | Gemini 3 Pro | prompt, image_urls, model | common; image_urls 1-5 | $0.20 | ~10s |
qwen-image/edit-2511 | Live | Qwen Image Edit 2511 | prompt, image_urls, model | common; image_urls 1-3 | $0.10 | ~15s |
Seedream-4.5-uncensored | Live | Seedream v4.5 | prompt, image_urls, model | common + seed; image_urls 1-5 | $0.10 | ~15s |
Wan-2.6 | Live | Wan 2.6 | prompt, image_urls, model | common + seed, negative_prompt; image_urls 1-5 | $0.10 | ~20s |
Wan-2.6-image-edit | Live | Wan 2.6 Image Edit | prompt, image_urls, model | common + seed, negative_prompt; image_urls 1-5 | $0.10 | ~15s |
group-edit | Live | Qwen Group Photo | prompt, image_urls, model | common + seed; image_urls 1-5 | $0.10 | ~20s |
xai/grok-imagine-image/edit | Live | Grok Imagine Edit | prompt, image_urls, model | common + seed; provider uses the first image | $0.10 | ~15s |
seedream-v5 | Live | Seedream v5 Lite | prompt, image_urls, model | common; image_urls 1-5 | $0.10 | ~15s |
nano-banana-2/edit | Live | Nano Banana 2 Edit | prompt, image_urls, model | common + resolution (0.5k, 1k, 2k, 4k), aspect_ratio, output_format (png, jpeg), enable_web_search, enable_image_search; image_urls 1-5 | 0.5k/1k/2k $0.10, 4k $0.20 | ~20s |
nano-banana-2/edit-fast | Live | Nano Banana 2 Edit Fast | prompt, image_urls, model | common + resolution (2k, 4k), aspect_ratio, output_format (png, jpeg); image_urls 1-5 | $0.10 | ~12s |
seedream-v4.5/edit-sequential | Live | Seedream v4.5 Edit Sequential | prompt, image_urls, model | common + seed, max_images (1-15); image_urls 1-5 | $0.10 | ~25s |
seedream-v5.0-lite/edit-sequential | Live | Seedream v5 Lite Edit Sequential | prompt, image_urls, model | common + max_images (1-15); image_urls 1-5 | $0.10 | ~25s |
wan-2.7-image-edit | Live | Wan 2.7 Image Edit | prompt, image_urls, model | common + seed; image_urls 1-5 | $0.10 | ~15s |
wan-2.7-image-edit-pro | Live | Wan 2.7 Image Edit Pro | prompt, image_urls, model | common + seed; image_urls 1-5 | $0.10 | ~20s |
gpt-image-2/edit | Live | GPT Image 2 Edit | prompt, image_urls, model | common + quality (low, medium, high), resolution (1k, 2k), aspect_ratio, output_format (png, jpeg, webp); image_urls 1-5 | low/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 ID | Status | Display name | Type | Required params | Optional supported params | Cost | ETA |
|---|---|---|---|---|---|---|---|
t2v-turbo | Live | Text-to-Video Turbo | Text-to-video | prompt, model | common + seconds (5, 8), resolution (480p, 720p), aspect_ratio, seed, negative_prompt | $0.40 | ~43s |
t2v-standard | Live | Text-to-Video Standard | Text-to-video | prompt, model | common + seconds, aspect_ratio (auto, 16:9, 9:16, 1:1) | $1.20 | ~63s |
cosmos-predict | Live | Cosmos Predict | Text-to-video | prompt, model | common + seconds, aspect_ratio | $0.80 | ~90s |
av-gen | Live | AV Gen | Text-to-video | prompt, model | common + seconds (5, 10, 15), resolution (720p, 1080p) | $1.00 | ~84s |
ltx-distilled | Live | LTX Distilled | Text-to-video | prompt, model | common + seconds, aspect_ratio | $0.3996 | ~63s |
seedance-2.0-t2v | Live | Seedance 2.0 T2V | Text-to-video | prompt, model | common + seconds (5, 10, 15), resolution (480p, 720p, 1080p), aspect_ratio | $1.80 default | ~70s |
seedance-2.0-fast-t2v | Live | Seedance 2.0 Fast T2V | Text-to-video | prompt, model | common + seconds (5, 10, 15), resolution (480p, 720p, 1080p), aspect_ratio | $0.60 default | ~45s |
wan-2.7-t2v | Live | Wan 2.7 T2V | Text-to-video | prompt, model | common + seconds (5, 10, 15), resolution (720p, 1080p), negative_prompt | $1.50 default | ~70s |
wan-2.2-ultra-fast-t2v | Live | Wan 2.2 Ultra-Fast T2V | Text-to-video | prompt, model | common + seconds (5, 8), resolution (480p, 720p), aspect_ratio, seed, negative_prompt | $0.60 default | ~25s |
happyhorse-1.0-t2v | Live | HappyHorse 1.0 T2V | Text-to-video | prompt, model | common + seconds (3-15), resolution (720p, 1080p), aspect_ratio (16:9, 9:16, 1:1), seed | $0.112-$0.224/sec | ~70s |
i2v-turbo | Live | Image-to-Video Turbo | Image-to-video | prompt, model, image_url | common + seconds (5, 8), resolution (480p, 720p), aspect_ratio, seed, negative_prompt | about $0.11 | ~39s |
i2v-standard | Live | Image-to-Video Standard | Image-to-video | prompt, model, image_url | common + seconds, resolution (480p, 720p), aspect_ratio (auto, 16:9, 9:16, 1:1) | $0.30-$0.60 | ~38s |
i2v-pro | Live | Image-to-Video Pro | Image-to-video | prompt, model, image_url | common + seconds, resolution (480p, 580p, 720p), aspect_ratio (16:9, 9:16, 1:1), end_image_url | $0.04-$0.08/sec | ~63s |
i2v-sora | Live | Image-to-Video Sora | Image-to-video | prompt, model, image_url | common + seconds (4, 8, 12), aspect_ratio (16:9, 9:16, 1:1) | about $0.11/sec | ~146s |
i2v-sora-pro | Live | Image-to-Video Sora Pro | Image-to-video | prompt, model, image_url | common + seconds (4, 8, 12), resolution (720p, 1080p), aspect_ratio (16:9, 9:16, 1:1) | $0.30-$0.50/sec | ~186s |
wan-2.6 | Live | Wan 2.6 | Image-to-video | prompt, model, image_url | common + seconds (5, 10, 15), resolution (720p, 1080p), negative_prompt | $0.10-$0.15/sec | ~84s |
wan-2.6-ultra | Live | Wan 2.6 Ultra | Image-to-video | prompt, model, image_url | common + seconds (5, 10, 15), resolution (720p, 1080p), negative_prompt | $0.10-$0.15/sec | ~60s |
wan-2.6-flash | Live | Wan 2.6 Flash | Image-to-video | prompt, model, image_url | common + seconds (5, 10, 15), resolution (720p, 1080p) | $0.05-$0.075/sec | ~45s |
wan-2.2-spicy | Live | Wan 2.2 Spicy | Image-to-video | prompt, model, image_url | common + seconds (5, 8), resolution (480p, 720p), seed | $0.024-$0.048/sec | ~40s |
wan-2.2-ultra-fast | Live | Wan 2.2 Ultra-Fast I2V | Image-to-video | prompt, model, image_url | common + seconds (5, 8), resolution (480p, 720p), aspect_ratio, seed, negative_prompt | $0.008-$0.016/sec | ~25s |
vidu-q3-spicy | Live | Vidu Q3 Spicy | Image-to-video | prompt, model, image_url | common + seconds (5, 10, 15), resolution (540p, 720p, 1080p) | $0.056-$0.128/sec | ~60s |
cosmos-predict-i2v | Live | Cosmos Predict I2V | Image-to-video | prompt, model, image_url | common + seconds, aspect_ratio | about $0.50 | ~90s |
grok-imagine-video | Live | Grok Imagine Video | Image-to-video | prompt, model, image_url | common + seconds (6, 10), resolution (480p, 720p), aspect_ratio (2:3, 3:2, 1:1, 16:9, 9:16) | about $0.04/sec | ~20s |
sora-2 | Live | Sora 2 | Smart-routed video | prompt, model | common + optional image_url, seconds (4, 8, 12), aspect_ratio (16:9, 9:16, 1:1) | about $0.11/sec | ~117s |
sora-2-pro | Live | Sora 2 Pro | Smart-routed video | prompt, model | common + 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-2.0 | Live | Seedance 2.0 I2V | Image-to-video | prompt, model, image_url | common + seconds (5, 10, 15), resolution (480p, 720p, 1080p), aspect_ratio | $0.12-$0.60/sec | ~70s |
seedance-2.0-fast | Live | Seedance 2.0 Fast I2V | Image-to-video | prompt, model, image_url | common + seconds (5, 10, 15), resolution (480p, 720p, 1080p), aspect_ratio | $0.10-$0.50/sec | ~45s |
seedance-2.0-spicy | Live | Seedance 2.0 Spicy I2V | Image-to-video | prompt, model, image_url | common + 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-spicy | Live | Seedance 2.0 Fast Spicy I2V | Image-to-video | prompt, model, image_url | common + 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-spicy | Live | Seedance v1.5 Pro Spicy | Image-to-video | prompt, model, image_url | common + seconds (4-12), resolution (480p, 720p, 1080p), aspect_ratio, generate_audio | $0.0096-$0.0416/sec | ~50s |
wan-2.7 | Live | Wan 2.7 I2V | Image-to-video | prompt, model, image_url | common + seconds (5, 10, 15), resolution (720p, 1080p), negative_prompt | $0.08-$0.12/sec | ~70s |
wan-2.7-pro | Live | Wan 2.7 Pro I2V | Image-to-video | prompt, model, image_url | common + seconds (5, 10, 15), resolution (1080p, 2k, 4k) | $0.12-$0.16/sec | ~70s |
wan-2.7-spicy | Live | Wan 2.7 Spicy I2V | Image-to-video | prompt, model, image_url | common + seconds (5, 10, 15), resolution (720p, 1080p) | $0.10-$0.15/sec | ~70s |
grok-imagine-video-reference | Live | Grok Imagine Reference-to-Video | Image-to-video | prompt, model, image_url | common + optional end_image_url, seconds (6, 10), resolution (480p, 720p) | about $0.04/sec | ~25s |
happyhorse-1.0 | Live | HappyHorse 1.0 I2V | Image-to-video | prompt, model, image_url | common + seconds (3-15), resolution (720p, 1080p), seed; aspect ratio follows the input image | $0.112-$0.224/sec | ~70s |
video-to-video | Live | Video to Video | Video-to-video | prompt, model, video_url | common + seconds, resolution (240p, 360p, 480p, 580p, 720p) | $0.04-$0.08/sec | ~175s |
wan-2.6-v2v | Live | Wan 2.6 V2V | Video-to-video | prompt, model, video_url | common + seconds (5, 10), resolution (720p, 1080p) | $0.10-$0.15/sec | ~90s |
wan-2.2-spicy-extend | Live | Wan 2.2 Spicy Extend | Video extend | prompt, model, video_url | common + seconds (5, 8), resolution (480p, 720p) | $0.024-$0.048/sec | ~40s |
grok-imagine-video-edit | Live | Grok Imagine Edit | Video edit | prompt, model, video_url | common + seconds (1-8), resolution (480p, 720p) | $0.06-$0.08/sec | ~95s |
wan-2.7-video-extend | Live | Wan 2.7 Video Extend | Video extend | prompt, model, video_url | common + seconds (5, 10, 15), resolution (720p, 1080p), negative_prompt | $0.08-$0.12/sec | ~70s |
grok-imagine-video-extend | Live | Grok Imagine Video Extend | Video extend | prompt, model, video_url | common + seconds (6, 10) | about $0.04/sec | ~25s |
happyhorse-1.0-video-edit | Live | HappyHorse 1.0 Video Edit | Video edit | prompt, model, video_url | common + 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-extend | Live | HappyHorse 1.0 Video Extend | Video extend | prompt, model, video_url | common + seconds (3-15), resolution (720p, 1080p), seed | $0.112-$0.224/sec | ~70s |
ultimate-video-upscaler | Live | Ultimate Video Upscaler | Video-to-video | prompt, model, video_url | common + 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-remover | Live | Video Watermark Remover | Video-to-video | prompt, model, video_url | common + 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 inadditional_settings (or as documented per endpoint):
| Parameter | Accepted values | Used by |
|---|---|---|
resolution | 0.5k, 1k, 2k, 4k, 8k | Models marked “Variable pricing: resolution” |
quality | low, medium, high | Models marked “Variable pricing: quality” |
aspect_ratio | 1:1, 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 |