API Documentation — Progressive Robot

Authentication

All API requests require a Bearer token unless noted as public

Create an API key in Settings → API Keys, then include it in the Authorization header of every request:

HTTP Header

            Authorization: Bearer pk_your_api_key_here

API keys inherit the permissions of the account that created them, including tier limits and admin access. The full key is only shown once at creation — store it securely.

API Key Management

Method	Endpoint	Description
GET	`/api/keys`	List your API keys (id, prefix, name, created_at, last_used, is_active)
POST	`/api/keys`	Create key — body: `{"name":"My App"}` — returns full key once
DELETE	`/api/keys/{id}`	Revoke an API key

Quick Start

Generate a video in three API calls

Start Here

1. Submit a generation → 2. Poll for completion → 3. Download the video.

cURL Example

# 1. Submit generation
curl -X POST https://video.progressiverobot.com/api/generate \
  -H "Authorization: Bearer pk_your_key" \
  -H "Content-Type: application/json" \
  -d '{"model":"wan-t2v","prompt":"A cinematic sunrise over mountains"}'

# Returns: {"job_id":"abc123","prompt_id":"...","credits_used":14,"credit_balance":486}

# 2. Poll status
curl https://video.progressiverobot.com/api/status?job_id=abc123 \
  -H "Authorization: Bearer pk_your_key"

# Returns: {"status":"completed","filename":"webgen_abc123_00001.mp4"}

# 3. Download video
curl -o video.mp4 https://video.progressiverobot.com/api/video/webgen_abc123_00001.mp4 \
  -H "Authorization: Bearer pk_your_key"

Python Example

import requests, time

API = "https://video.progressiverobot.com"
KEY = "pk_your_key"
HDR = {"Authorization": f"Bearer {KEY}"}

# 1. Submit
r = requests.post(f"{API}/api/generate", headers=HDR, json={
    "model": "wan-t2v",
    "prompt": "A cinematic sunrise over mountains"
})
job_id = r.json()["job_id"]

# 2. Poll
while True:
    s = requests.get(f"{API}/api/status", headers=HDR,
                     params={"job_id": job_id}).json()
    if s["status"] == "completed":
        break
    if s["status"] == "error":
        raise Exception(s.get("error", "Generation failed"))
    time.sleep(3)

# 3. Download
vid = requests.get(f"{API}/api/video/{s['filename']}", headers=HDR)
with open("video.mp4", "wb") as f:
    f.write(vid.content)

JavaScript Example

const API = "https://video.progressiverobot.com";
const KEY = "pk_your_key";
const headers = { "Authorization": `Bearer ${KEY}`, "Content-Type": "application/json" };

// 1. Submit
const gen = await fetch(`${API}/api/generate`, {
  method: "POST", headers,
  body: JSON.stringify({ model: "wan-t2v", prompt: "A cinematic sunrise over mountains" })
}).then(r => r.json());

// 2. Poll
let status;
do {
  await new Promise(r => setTimeout(r, 3000));
  status = await fetch(`${API}/api/status?job_id=${gen.job_id}`, { headers }).then(r => r.json());
} while (status.status === "processing");

// 3. Download
const blob = await fetch(`${API}/api/video/${status.filename}`, { headers }).then(r => r.blob());

Video Generation

Text-to-video, image-to-video, extend, and video-to-video

Core

POST /api/generate

Queue a text-to-video or image-to-video generation. Returns a job_id to poll.

Request Body (JSON)
{
  "model": "wan-t2v",
  "prompt": "A cinematic shot of a golden sunrise over mountains",
  "negative_prompt": "blurry, distorted",
  "width": 848,
  "height": 480,
  "frames": 41,
  "steps": 4,
  "cfg": 1,
  "seed": -1,
  "sampler": "sa_solver",
  "scheduler": "beta",
  "shift": 8,
  "frame_rate": 24
}

Parameters

Field	Type	Required	Description
`prompt`	string	Yes	Text description (max 2000 chars)
`model`	string	No	Model ID — see Models
`negative_prompt`	string	No	What to avoid in the output
`width`	int	No	Video width in pixels
`height`	int	No	Video height in pixels
`frames`	int	No	Number of frames (tier-limited)
`steps`	int	No	Inference steps — more = higher quality, higher cost
`cfg`	number	No	Classifier-free guidance scale
`seed`	int	No	Random seed (-1 for random)
`sampler`	string	No	Sampler name (e.g. sa_solver, euler, dpmpp_2m)
`scheduler`	string	No	Scheduler name (e.g. beta, normal, karras)
`shift`	number	No	Flow-shift parameter
`frame_rate`	int	No	Output frame rate (default 24)
`project_id`	int	No	Link generation to a studio project

Response
{
  "job_id": "abc12345",
  "prompt_id": "...",
  "credits_used": 14,
  "credit_balance": 486
}

Error — Insufficient Credits
{
  "error": "Not enough credits",
  "cost": 14,
  "balance": 3,
  "upgrade_url": "/pricing"
}

GET /api/status?job_id={id}

Poll for generation progress. Call every 2-5 seconds until status is completed or error.

Response (processing)
{ "status": "processing" }

Response (completed)
{ "status": "completed", "filename": "webgen_abc12345_00001.mp4" }

Response (error)
{ "status": "error", "error": "Generation failed" }

GET /api/video/{filename}

Download the generated video file. Returns raw video/mp4 bytes. You must own the video, or provide a valid share ?token=.

GET /api/generations

List your video generation history with full metadata.

Query Param	Type	Default	Description
`limit`	int	50	Max results (up to 200)
`offset`	int	0	Pagination offset

Response
{
  "generations": [
    {
      "id": 1, "job_id": "abc123", "model": "wan-t2v",
      "prompt": "...", "negative_prompt": "...",
      "filename": "webgen_abc123_00001.mp4",
      "width": 848, "height": 480, "frames": 41,
      "steps": 4, "cfg": 1, "seed": 42,
      "sampler": "sa_solver", "scheduler": "beta",
      "frame_rate": 24, "shift": 8,
      "is_favorite": 0, "is_public": 0,
      "share_token": null, "status": "completed",
      "created_at": "2026-03-30 12:00:00"
    }
  ],
  "total": 142
}

Additional Video Endpoints

Method	Endpoint	Body / Params	Description
DELETE	`/api/generations/{id}`	—	Delete a generation and its video file
POST	`/api/generations/{id}/favorite`	—	Toggle favourite — returns `is_favorite`
POST	`/api/generations/{id}/share`	—	Create share link — returns `share_token`
POST	`/api/generations/{id}/public`	—	Toggle public gallery visibility
GET	`/api/share/{token}`	—	Public — get shared video metadata
GET	`/api/gallery/community`	—	Public — browse public gallery
POST	`/api/cancel`	`{"job_id":"..."}`	Cancel a running generation
GET	`/api/queue`	—	Queue length, your active jobs, and position
GET	`/api/comfyui/status`	—	Check if backend GPU is online
GET	`/api/generation-cost`	`?model=&frames=&steps=`	Quote credit cost without generating
POST	`/api/extend-video`	`{"video_filename":"...","generation_id":1}`	Extract last frame for video extension via I2V
POST	`/api/generate-v2v`	`{"video_filename":"...","prompt":"...","strength":0.6}`	Video-to-video style transfer

Image Generation

Generate images and upload input images for I2V

POST /api/generate-image

Queue one or more image generations. Returns an array of job IDs to poll via /api/status.

Request Body (JSON)
{
  "prompt": "A futuristic city at sunset, neon lights",
  "model": "sd15",
  "num_images": 2,
  "negative_prompt": "blurry",
  "seed": -1,
  "steps": 20,
  "cfg": 7,
  "width": 512,
  "height": 512
}

Response
{
  "jobs": [
    { "job_id": "img_001", "prompt_id": "...", "seed": 42 },
    { "job_id": "img_002", "prompt_id": "...", "seed": 43 }
  ],
  "credits_used": 4,
  "credit_balance": 496
}

Image Endpoints

Method	Endpoint	Description
GET	`/api/image-models`	List image models (id, name, defaults, credit_cost)
GET	`/api/image-generations`	List image history — `?limit=&offset=`
DELETE	`/api/image-generations/{id}`	Delete an image generation
GET	`/api/image/{filename}`	Download a generated image
POST	`/api/upload-image`	Upload image for I2V (multipart, PNG/JPEG/WebP, max 10 MB)
GET	`/api/input-image/{filename}`	Serve uploaded/extracted input image

Audio, Subtitles & TTS

Generate music, speech, subtitles, and mix into videos

POST /api/generate-audio

Generate music or sound effects from a text description.

Request Body
{
  "prompt": "Upbeat electronic music with synth pads",
  "duration_seconds": 30,
  "tags": "electronic, upbeat"
}

POST /api/tts/generate

Generate voice narration from text. Requires Creator tier or higher.

Request Body
{
  "text": "Welcome to Progressive Robot, the AI video platform.",
  "voice_id": "en_gb_male",
  "speed": 1.0
}

Response
{
  "audio_url": "/api/audio/tts_abc123.wav",
  "duration_seconds": 4.2,
  "credit_balance": 494
}

All Audio & Subtitle Endpoints

Method	Endpoint	Body / Params	Description
POST	`/api/generate-audio`	`{"prompt","duration_seconds","tags"}`	Generate music/SFX (8 credits per 30s)
GET	`/api/audio-generations`	—	List audio generation history
DELETE	`/api/audio-generations/{id}`	—	Delete audio generation
GET	`/api/audio/{filename}`	—	Download generated audio file
POST	`/api/video/add-audio`	`{"video_filename","audio_filename"}`	Merge audio onto a video
POST	`/api/subtitles/generate`	`{"video_filename","language":"en"}`	Auto-generate subtitles with Whisper (5 credits)
GET	`/api/subtitles/{name}.srt`	—	Download subtitle file
POST	`/api/subtitles/burn`	`{"video_filename","srt_filename","style"}`	Burn subtitles into video (styles: default, bold-yellow, minimal)
POST	`/api/subtitles/translate`	`{"srt_filename","target_language"}`	AI translate subtitles (Pro+ required, 5 credits)
GET	`/api/tts/voices`	—	List available TTS voices
POST	`/api/tts/generate`	`{"text","voice_id","speed"}`	Generate speech (Creator+, 6 credits/min)
POST	`/api/tts/add-to-video`	`{"video_filename","tts_filename","offset_seconds","volume"}`	Mix TTS audio into a video

TTS Voices

Voice ID	Description
`en_gb_male`	British English — Male
`en_gb_female`	British English — Female
`en_us_male`	American English — Male
`en_us_female`	American English — Female

Editing & Tools

Trim, crop, resize, upscale, background removal, face swap, and more

POST /api/edit/trim

Trim a video to a specific time range.

Request Body
{
  "video_filename": "webgen_abc123_00001.mp4",
  "start_seconds": 1.5,
  "end_seconds": 4.0
}

Response
{ "filename": "trimmed_abc123.mp4", "credit_balance": 497 }

Edit Endpoints (3 credits each)

Method	Endpoint	Key Parameters	Description
POST	`/api/edit/trim`	`start_seconds, end_seconds`	Trim video to time range
POST	`/api/edit/speed`	`speed_factor` (0.25–4.0)	Change playback speed
POST	`/api/edit/crop`	`x, y, width, height`	Crop video region
POST	`/api/edit/resize`	`preset` or `width, height`	Resize & pad video (presets: 1080p, 720p)
POST	`/api/edit/text-overlay`	`text, position, font_size, color, start_time, end_time`	Burn text overlay onto video
POST	`/api/edit/merge`	`video_filenames` (array, 2–20)	Concatenate multiple videos

AI Tools

Method	Endpoint	Key Parameters	Credits	Description
POST	`/api/tools/remove-background`	Multipart image upload	1	AI background removal
POST	`/api/tools/upscale-video`	`video_filename, scale_factor` (2–4)	~2/10s	Upscale video (Creator+)
POST	`/api/tools/face-swap`	Multipart: two image files	1	AI face swap (Pro+)
POST	`/api/tools/extract-frames`	`video_filename, mode`	1	Extract frames (first, last, middle, all_1fps)
POST	`/api/tools/trim-video`	`video_filename, start_time, end_time`	1	Simple trim utility
POST	`/api/tools/video-to-gif`	`video_filename, width, fps`	1	Convert video to animated GIF
POST	`/api/tools/add-watermark`	Multipart: `video_filename, type, text/image`	1	Add text or image watermark

Studio & Projects

Multi-shot project management and AI script breakdown

POST /api/studio/script-to-shots

Use AI to break a script into individual shot prompts.

Request Body
{
  "script": "A hero walks through a dystopian city. She finds a glowing artifact...",
  "shot_count": 4,
  "style": "cinematic sci-fi"
}

Response
{
  "shots": [
    "Wide establishing shot of a crumbling cityscape...",
    "Medium shot tracking the hero walking through debris...",
    "Close-up of glowing artifact pulsing with light...",
    "Hero reaches out to touch the artifact, dramatic lighting..."
  ]
}

Project Endpoints

Method	Endpoint	Body / Params	Description
GET	`/api/projects`	—	List projects (with shot_count and cover)
POST	`/api/projects`	`{"name":"My Film"}`	Create project
GET	`/api/projects/{id}`	—	Get project with shots array and generations
PUT	`/api/projects/{id}`	`{"name","description","model"}`	Update project metadata
DELETE	`/api/projects/{id}`	—	Delete project and all shots
POST	`/api/projects/{id}/duplicate`	—	Duplicate project with all shots & elements
POST	`/api/projects/{id}/export`	`{"resolution":"1080p"}`	Export project — concatenates shot videos

Shot Endpoints

Method	Endpoint	Body / Params	Description
POST	`/api/projects/{id}/shots`	`{"prompt","notes","duration","shot_type","camera_move","transition"}`	Add shot to project
PUT	`/api/projects/{id}/shots/{shotId}`	Same fields as above + `filename`	Update shot (link a generation via filename)
DELETE	`/api/projects/{id}/shots/{shotId}`	—	Delete shot
POST	`/api/projects/{id}/shots/reorder`	`{"order":[3,1,2]}`	Reorder shots by ID array

Elements & Comments

Method	Endpoint	Description
GET	`/api/projects/{id}/elements`	List project elements (characters, props, locations)
POST	`/api/projects/{id}/elements`	Create element
PUT	`/api/projects/{id}/elements/{eid}`	Update element
DELETE	`/api/projects/{id}/elements/{eid}`	Delete element
GET	`/api/projects/{id}/comments`	List project comments
POST	`/api/projects/{id}/comments`	Add comment — `{"text","shot_id"}`
DELETE	`/api/projects/{id}/comments/{cid}`	Delete comment

Hosting & Landing Pages

Create hosted video landing pages with analytics — Pro tier and above

POST /api/hosting/pages

Create a hosted landing page for a video. Returns a public URL and embed code.

Request Body
{
  "generation_id": 42,
  "title": "Product Demo Video",
  "description": "Our latest AI-generated product showcase",
  "slug": "product-demo",
  "cta_text": "Learn More",
  "cta_url": "https://example.com",
  "allow_embed": true
}

Response
{
  "id": 1,
  "slug": "product-demo",
  "page_url": "https://video.progressiverobot.com/v/product-demo",
  "embed_code": "<iframe src=\".../v/product-demo/embed\"></iframe>"
}

Hosting Endpoints

Method	Endpoint	Description
GET	`/api/hosting/pages`	List your hosted pages
GET	`/api/hosting/pages/{id}`	Get page details
PUT	`/api/hosting/pages/{id}`	Update page (title, description, CTA, password, visibility)
DELETE	`/api/hosting/pages/{id}`	Delete hosted page
GET	`/api/hosting/pages/{id}/analytics`	View analytics (total views, unique views, referrers, daily breakdown)

Community Prompts

Browse, share, and vote on prompts

Method	Endpoint	Auth	Description
GET	`/api/community/prompts`	Public	Browse approved prompts — `?sort=popular&tag=cinematic&model=wan-t2v&page=1`
POST	`/api/community/prompts`	Auth	Submit a prompt for moderation — `{"prompt","model","title","tags"}`
POST	`/api/community/prompts/{id}/vote`	Auth	Upvote or downvote — `{"vote":1}`
POST	`/api/community/prompts/{id}/use`	Auth	Increment use count and retrieve prompt text
DELETE	`/api/community/prompts/{id}`	Auth	Delete own prompt (admin can delete any)

Stock Media

Search and download royalty-free videos, images, and music — Creator tier and above

Method	Endpoint	Params	Description
GET	`/api/stock/videos`	`?query=&page=&per_page=`	Search Pexels videos (max 30/page)
GET	`/api/stock/images`	`?query=&page=&per_page=`	Search Pexels images (max 30/page)
GET	`/api/stock/music`	`?query=`	Search Pixabay music
POST	`/api/stock/download`	`{"url","type"}`	Download stock asset to local storage

Organisations

Team collaboration and shared projects — Pro tier and above

Method	Endpoint	Body / Params	Description
POST	`/api/orgs`	`{"name":"My Team"}`	Create organisation (Pro+)
GET	`/api/orgs`	—	List your organisations
POST	`/api/orgs/{id}/invite`	`{"email","role"}`	Invite member (roles: member, admin, reviewer)
POST	`/api/orgs/accept-invite`	`{"token":"..."}`	Accept invitation
GET	`/api/orgs/{id}/members`	—	List org members
PUT	`/api/orgs/{id}/members/{uid}/role`	`{"role":"admin"}`	Change member role (org admin only)
DELETE	`/api/orgs/{id}/members/{uid}`	—	Remove member (org admin only)
GET	`/api/orgs/{id}/projects`	—	List organisation projects
POST	`/api/orgs/{id}/projects`	`{"name":"Team Project"}`	Create organisation project

Brand Kits

Custom branding overlays, logos, and intros — Pro tier and above

POST /api/brand-kits

Create a brand kit with custom colours, fonts, and positioning.

Request Body
{
  "name": "My Brand",
  "primary_color": "#7c3aed",
  "secondary_color": "#1e1b4b",
  "font_family": "Inter",
  "default_text_position": "bottom-right",
  "default_text_color": "#ffffff",
  "default_text_size": 24
}

Method	Endpoint	Description
GET	`/api/brand-kits`	List brand kits
PUT	`/api/brand-kits/{id}`	Update brand kit settings
DELETE	`/api/brand-kits/{id}`	Delete brand kit
POST	`/api/brand-kits/{id}/upload-logo`	Upload logo (multipart)
POST	`/api/brand-kits/{id}/upload-intro`	Upload intro clip (multipart)
POST	`/api/brand-kits/{id}/apply`	Apply brand kit to video — `{"video_filename":"..."}`

Prompt Tools & Templates

AI prompt generation, autocomplete, and saved templates

POST /api/generate-prompt

Use AI to generate or enhance video prompts from a simple idea.

Request Body
{
  "idea": "cat in space",
  "model": "wan",
  "style": "cinematic",
  "mood": "epic",
  "count": 3,
  "enhance": true
}

Response
{
  "prompts": [
    "A majestic orange tabby cat floating weightlessly...",
    "Cinematic close-up of a cat in a space helmet...",
    "Wide shot of a cat leaping between asteroids..."
  ],
  "negative": "blurry, distorted, low quality"
}

Method	Endpoint	Description
GET	`/api/prompts/autocomplete`	Get prompt suggestions from your history
GET	`/api/templates`	List saved prompt templates
POST	`/api/templates`	Save template — `{"name","prompt","negative_prompt","model"}`
DELETE	`/api/templates/{id}`	Delete template

Settings, Profile & Billing

Account management, subscription, and credit top-ups

Method	Endpoint	Body / Params	Description
Auth & Session
GET	`/api/auth/check`	—	Current auth state, tier, credit balance, limits
POST	`/api/signup`	`{"username","password","email"}`	Create account (public)
POST	`/api/login`	`{"username","password"}`	Log in (public)
POST	`/api/logout`	—	Log out (clears session cookie)
POST	`/api/password-reset/request`	`{"username":"..."}`	Request password reset email (public)
POST	`/api/password-reset/reset`	`{"token","new_password"}`	Complete password reset (public)
Profile
GET	`/api/profile`	—	Get profile (username, display_name, bio, avatar)
POST	`/api/profile`	`{"display_name","bio","profile_public"}`	Update profile
POST	`/api/profile/avatar`	Multipart image upload	Upload avatar
Settings
POST	`/api/settings/change-password`	`{"current_password","new_password"}`	Change password (min 8 chars)
POST	`/api/settings/email`	`{"email":"..."}`	Update email address
POST	`/api/settings/theme`	`{"theme":"dark"}`	Set theme (dark or light)
Credits & Billing
GET	`/api/credits`	—	Credit balance, tier, monthly allowance
GET	`/api/credits/history`	—	Credit transaction ledger
POST	`/api/credits/topup`	`{"credits":500}`	Purchase credits (100–50,000 at 1p each)
GET	`/api/subscription`	—	Current subscription details
POST	`/api/stripe/create-checkout`	`{"tier":"creator"}`	Start Stripe subscription checkout
POST	`/api/stripe/create-portal`	—	Open Stripe customer portal (manage billing)
GET	`/api/pricing`	—	Public — tier pricing and credit cost rules
GET	`/api/stripe/config`	—	Public — Stripe publishable key
Analytics
GET	`/api/analytics/usage`	—	Per-day generation and credit spending breakdown
GET	`/api/analytics/summary`	—	Total generations, images, video minutes, favourite model

Available Models

All supported generation models and their capabilities

Video Models (Text-to-Video)

Model ID	Name	Best For
`wan-t2v`	WAN 2.2	Rich cinematic visuals, longer videos
`ltx-t2v`	LTX 2.3	Fast generation, HD output
`ltx-quality`	LTX Quality	Highest quality, 2-pass upscale to 4K
`hunyuan-t2v`	Hunyuan	Smooth motion, natural movement
`hunyuan15-t2v`	Hunyuan 1.5	Improved motion, latest Hunyuan release
`cogvideo-t2v`	CogVideoX 1.5	High fidelity 5B model, diverse styles
`animatediff`	AnimateDiff	SD 1.5-based animation, fast & lightweight
`ltx-camera`	LTX Camera Control	Camera dolly movements (in, out, left, right) via LoRA
`ltx-control`	LTX ControlNet	ControlNet-guided generation (depth, edge, pose)
`wan-vace`	WAN VACE	Video conditioning & editing with subject/scene control
`wan-animate`	WAN Animate	Character animation from a single reference image

Video Models (Image-to-Video)

Model ID	Name	Description
`hunyuan15-i2v`	Hunyuan 1.5 I2V	Animate a still image into video
`ltx-i2v`	LTX 2.3 I2V	Fast image-to-video generation
`svd-i2v`	SVD XT I2V	Stable Video Diffusion image-to-video
`wan-i2v`	WAN 2.2 I2V	High-quality 14B image-to-video with Lightx2v turbo

Video Models (First-Last Frame)

Model ID	Name	Description
`ltx-flf`	LTX 2.3 First-Last Frame	Interpolate between two keyframe images with prompt guidance
`wan-flf`	WAN 2.2 First-Last Frame	WAN 14B first & last frame interpolation with Lightx2v turbo

Video Models (Sound-to-Video)

Model ID	Name	Description
`wan-s2v`	WAN 2.2 Sound-to-Video	Generate talking-head video from a portrait image + audio clip

Specialised Models

Model ID	Name	Description
`liveportrait`	LivePortrait	Animate a portrait photo with facial expressions from a driving video
`dreamidv`	DreamID-V	Face identity transfer — insert a face into generated video
`echomimic`	EchoMimic	Audio-driven talking portrait from a single photo + audio clip
`hunyuan3d`	Hunyuan3D v2	Generate 3D model assets from a text prompt or reference image

Image Models

Model ID	Name	Credit Cost
`sd15`	Stable Diffusion 1.5	2 credits per image
`flux`	Flux 2 Klein	5 credits per image
`flux-dev`	Flux 2 Dev	8 credits per image
`flux-edit`	Flux 2 Image Edit	6 credits per image

Use GET /api/models for video models or GET /api/image-models for image models to retrieve live defaults and parameters at runtime.

Credit Costs

How credits are calculated for each operation

Video Generation Cost Formula

cost = base + (frames × per_frame) + (steps × per_step)

Model	Base	Per Frame	Per Step	Example (41 frames, 4 steps)
`wan-t2v`	10	0.20	0.50	20.2 → 21 credits
`ltx-t2v`	8	0.15	0.30	15.35 → 16 credits
`ltx-quality`	15	0.25	0.40	26.85 → 27 credits
`hunyuan-t2v`	12	0.20	0.40	21.8 → 22 credits
`hunyuan15-t2v`	12	0.20	0.40	21.8 → 22 credits
`hunyuan15-i2v`	15	0.25	0.50	27.25 → 28 credits
`ltx-i2v`	12	0.20	0.40	21.8 → 22 credits
`cogvideo-t2v`	12	0.20	0.40	21.8 → 22 credits
`animatediff`	6	0.10	0.30	8.8 → 9 credits
`svd-i2v`	10	0.15	0.40	17.75 → 18 credits
`wan-i2v`	12	0.20	0.50	22.2 → 23 credits
`ltx-flf`	12	0.15	0.30	18.55 → 19 credits
`wan-s2v`	15	0.25	0.50	27.25 → 28 credits
`wan-flf`	12	0.20	0.50	22.2 → 23 credits
`ltx-camera`	10	0.15	0.30	17.15 → 18 credits
`ltx-control`	12	0.15	0.30	18.55 → 19 credits
`wan-vace`	15	0.25	0.50	27.25 → 28 credits
`wan-animate`	18	0.30	0.50	32.3 → 33 credits
`liveportrait`	8	0.10	—	12.1 → 13 credits
`hunyuan3d`	20	—	0.80	23.2 → 24 credits
`dreamidv`	15	0.20	0.40	24.8 → 25 credits
`echomimic`	12	0.15	0.30	18.55 → 19 credits
`v2v`	3	—	—	3 credits (flat)

Other Operation Costs

Operation	Credits
Image generation (SD 1.5)	2 per image
Image generation (Flux 2 Klein)	5 per image
Image generation (Flux 2 Dev)	8 per image
Image generation (Flux 2 Edit)	6 per image
Audio generation (ACE-Step)	8 per 30 seconds (pro-rated)
TTS voice generation	6 per minute (pro-rated)
Subtitle generation (Whisper)	5 flat
Subtitle translation	5 flat
Video edit (trim, speed, crop, resize, text overlay, merge)	3 each
Remove background	1
Face swap	1
Extract frames	1
Trim video (tools)	1
Video to GIF	1
Add watermark	1
Upscale video	~2 per 10 seconds (min 2)
Video-to-video	~3 per 10 seconds (min 3)
Project export	max(3, 2 × clip count)
Merge videos	max(3, 2 × clip count)

Use GET /api/generation-cost?model=wan-t2v&frames=41&steps=4 to get an exact quote before generating.

Subscription Tiers

Feature limits by plan

Tier	Monthly Credits	Max Resolution	Max Frames	Watermark
Free	150	480p	81	Yes
Starter	500	1080p	121	No
Creator	1,500	4K	201	No
Pro	5,000	4K	301	No
Studio	15,000	4K	301	No
Enterprise	50,000	4K	999	No

Some features require specific tiers: Stock Media (Creator+), TTS (Creator+), Hosting (Pro+), Organisations (Pro+), Brand Kits (Pro+), Subtitle Translation (Pro+), Upscale (Creator+), Face Swap (Pro+).

Rate Limits

Request limits and body size constraints

API Rate Limit10 requests per 60 seconds per user

Signup Limit5 per IP per hour

Login Limit10 per IP per 5 minutes

Max POST Body10 MB

Max JSON Body1 MB

Max Prompt Length2,000 characters

Image Upload Limit10 MB (PNG, JPEG, WebP)

Error Handling

Standard error response format and HTTP status codes

All API errors return JSON with an error field. Some errors include additional context fields.

Standard Error
{ "error": "Unauthorized" }              // 401
{ "error": "Forbidden" }                 // 403
{ "error": "Not found" }                 // 404
{ "error": "Rate limit exceeded" }       // 429

Credit Error (includes cost data)
{
  "error": "Not enough credits",
  "cost": 21,
  "balance": 5,
  "upgrade_url": "/pricing"
}

HTTP Status Codes

Code	Meaning
200	Success
400	Bad request — missing or invalid parameters
401	Unauthorized — missing or invalid API key
403	Forbidden — insufficient tier or permissions
404	Resource not found
429	Rate limit exceeded
500	Internal server error