Netwrck API Documentation
Build powerful AI applications with our comprehensive suite of APIs. Generate stunning images, create dynamic videos, and integrate cutting-edge AI into your projects.
API Endpoints
POST /api/create-ai
Create AI characters with avatar URL, bytes, or file upload
Input: api_key, name, description, greeting, avatar_url/avatar_bytes
Output: id, url_name, avatar_file_name, uploaded_via_api
Cost: free, authenticated only
POST /api/chatpred_or
Chat with a Netwrck character by exact name or URL name
Input: query, character, model_name, use_usage_credits
Output: character response
Cost: model token rates
POST /api/create-post
Publish image or video content to the gallery
Input: api_key, text, media_url/media_bytes/media file, tags
Output: post id, media_url, author_user_id, uploaded_via_api
Cost: free, authenticated only
POST /api/ra1
Generate AI images from text prompts
Input: api_key, prompt, size
Output: image_url, credits_charged
Cost: $0.04/image
POST /api/ra2
Generate AI images from text prompts
Input: api_key, prompt, size or resolution, num_images, seed
Output: image_url, images, credits_charged
Cost: $0.04/image (4 credits)
POST /api/ra2-image-editor
Edit an image from a source image and text prompt
Input: api_key, image file or image_base64/image_url, prompt, size or resolution, seed
Output: image_url, credits_charged
Cost: $0.04/edit (4 credits)
POST /api/zimage
Generate anime-style AI images
Input: api_key, prompt, size
Output: image_url, credits_charged
Cost: $0.007/image
POST /api/nano-banana
Gemini Flash photorealistic image generation
Input: api_key, prompt, aspect_ratio, resolution
Output: image_url, credits_charged
Cost: from $0.07/image (up to 4K)
POST /api/smart-resize
Composition-aware image resize to exact target sizes
Input: api_key, image_url, target_sizes
Output: images, result, credits_charged
Cost: $0.18/output + $0.06/request
POST /api/wan
Transform images into videos
Input: api_key, image_url, prompt
Output: video_url, seed
Cost: $0.30/video
POST /api/ltx-video-v097
Simple image animations
Input: api_key, image_url, prompt
Output: video_url, credits_charged
Cost: $0.05/video
POST /api/ltx-2
High-fidelity image or text to video
Input: api_key, prompt, image_url (optional)
Output: video, credits_charged
Cost: $0.072/sec (1080p)
POST /api/ltx-text-to-video
LTX 2.3 text to video with audio
Input: api_key, prompt, duration, resolution
Output: video, credits_charged
Cost: $0.048/sec (1080p), up to 20s
POST /api/ltx-2.3-image-to-video
LTX 2.3 image to video with audio
Input: api_key, prompt, image_url, duration, resolution
Output: video, credits_charged
Cost: $0.048/sec (1080p), up to 20s
POST /api/ra2v
Smart video generation
Input: api_key, prompt, image_url (optional)
Output: video_url, backend_used
Cost: $1.00
POST /api/remove-background
Remove image backgrounds with BiRefNet v2
Input: api_key, image_url
Output: image (transparent PNG)
Cost: $0.02/image
POST /api/remove-background-video
Remove video backgrounds with BiRefNet v2
Input: api_key, video_url
Output: video (transparent)
Cost: $0.50/video
POST /api/video-editor/render
Server-side renders for timeline projects
Input: api_key, project, format
Output: job_id, status
Cost: $0.01/sec
Notes: Public clip URLs required
POST /api/translate
Translate text into 18 languages with per-word readings
Input: text, target_lang
Output: lines[] (src, dst, words[])
Cost: free, rate limited, no key required
GET /api/emoji-search
Semantic emoji search
Input: q, limit
Output: results[] (emoji, category, score)
Cost: free, no key required
GET /api/search-aiimages
Search AI generated images
Input: query, limit, offset
Output: image list (name, avatar_file_name)
Cost: free, no key required
GET /api/get-tags-for-prompt
Extract and expand art prompt tags
Input: prompt, max_related
Output: extracted_tags, related_tags, category_tags
Cost: free, no key required
POST /api/video-relight
Relight a video with MiniMax H3 Max Relight (async, poll /api/fal/status/<job_id>)
Input: video_url, reference_image_url (lighting sphere), resolution (480P, 768P, 1080P, 2K), aspect_ratio, seed
Output: job_id, status_url, credits_charged; then video_url
Cost: per source second (3-15 s): 5.5, 8.8, 17.6 or 35.2 credits, rounded up per clip
POST /api/mesh-texturing
Texture an untextured 3D mesh from a reference image or prompt (async, poll /api/fal/status/<job_id>)
Input: mesh_url (.glb, .gltf, .obj, .ply, .stl), image_url or prompt, resolution (1024, 2048), seed, steps
Output: job_id, status_url, credits_charged; then result.glb_url, result.albedo_url, result.views_url
Cost: 12 credits at 1024, 36 credits at 2048; refunded if the job fails
POST /api/lyria
Generate music with Google Lyria 3 (Pro songs or Clip)
Input: prompt, model (pro, clip), output_format
Output: audio, duration_seconds, credits_charged, cost_usd
Cost: 5 credits per Clip, 10 per Pro; refunded on failure
POST /api/google-tts
Gemini 3.1 Flash TTS narration and two-speaker dialogue
Input: input (up to 20,000 characters), voice, language, temperature, speaker_voices (max 2), auto_emotion
Output: audio_base64 or audio_url, format, input_tokens, output_tokens, credits_charged
Cost: metered: $1.44 per 1M text tokens and $28.80 per 1M audio tokens; reserved up front, settled to actual usage
POST /api/infinitalk
Portrait plus speech to a talking video (async by default, response_mode=sync to wait)
Input: image_url or portrait_slug, text or audio_url, backend (manifold-h3, infinitalk), seconds, resolution, seed, response_mode
Output: job_id, status_url, credits_charged, cost_usd; then result video
Cost: 30 credits per second (H3), 30 per second (InfiniTalk); refunded if the job fails
POST /api/talking-character
Talking portrait or lipsync retalk across several backends (GET /api/talking-character/backends lists rates)
Input: backend, image_url or portrait_slug or video_url, text or audio_url, voice_key, seconds, resolution, response_mode
Output: job_id, status_url, credits_charged, cost_usd; or result when response_mode=sync
Cost: per second of speech, provider price plus 20%: OmniHuman 19.2 credits per second; text-to-speech about 6 credits per 1,000 characters
POST /api/manifoldgen/video
ManifoldGen H3 video: text, image, reference, video-to-video, pose and orbit (async, poll /api/fal/status/<job_id>)
Input: mode, prompt, image_url, video_url, reference_url, duration, aspect_ratio, quality (preview, balanced, native), include_audio, seed
Output: job_id, status_url, credits_charged
Cost: 46, 71 or 101 credits per 5 seconds at preview, balanced or native quality; pose and orbit modes priced per request
POST /api/music-generator
Full songs and clips from a prompt and optional lyrics (async, poll /api/music-generator/status)
Input: prompt, lyrics, is_instrumental, duration, length (clip, song), format, seed, title
Output: job_id, status, status_url, credits_charged
Cost: 50 credits per generation on the default model; Manifold Music: 8 per clip, 20 per song
POST /api/gpt-image-2
OpenAI GPT Image 2 text-to-image
Input: prompt, num_images, size (1024x1024, 1536x1024, 1024x1536, auto), quality
Output: image_url, images, width, height, credits_charged, cost
Cost: 26 credits per image
POST /api/iclight-v2
Relight an image from a text lighting prompt with IC-Light V2
Input: image_url, prompt, negative_prompt, initial_latent, image_size, num_images, seed
Output: image_url, images, credits_charged, cost
Cost: 30 credits per image
POST /api/cutout
Transparent-background cutout job (poll GET /api/cutout/status?job=<id>)
Input: image_url, decontaminate, cache, foreground_threshold
Output: job id and status; result is a WebP with alpha
Cost: 2 credits per cutout
POST /fal
Model gateway for 3D, sound effects, voice and upscaling. Set model_name and add response_mode=polling for async (poll /api/fal/status/<job_id>)
Input: model_name (fal-ai/pixal3d, fal-ai/meshy/v6/image-to-3d, tripo3d/p1/image-to-3d, tripo3d/p1/text-to-3d, fal-ai/elevenlabs/sound-effects/v2, fal-ai/f5-tts, fal-ai/creative-upscaler, fal-ai/birefnet/v2) plus that model's own fields
Output: model result inline, or job_id and status_url when polling
Cost: Pixal3D 36-51 credits, Meshy v6 96, Tripo3D 48-60, sound effects 0.24 per second, F5 voice clone 6 per 1,000 characters, upscaler 15, background removal 2
Quick Start
Make Request
curl -X POST https://netwrck.com/api/ra1 \
-H "Content-Type: application/json" \
-d '{
"api_key": "YOUR_API_KEY",
"prompt": "A mountain landscape",
"size": "1024x1024"
}'
3. Get Response
{
"image_url": "https://storage.../image.png",
"prompt_used": "A mountain landscape",
"credits_charged": 4
}
Only charged for successful generations. Test with our interactive tester below.
Interactive API Tester
Request
Response
Explore Our APIs
Click on any API card above or use the sidebar to view detailed documentation for each endpoint. Each API page includes complete parameter descriptions, code examples in multiple languages, and best practices.
📸 RA1 Art Generator
High-quality AI image generation from text prompts
View Documentation →
RA2 Art Generator
High-quality AI image generation from text prompts
View Documentation →
RA2 Image Editor
Edit images from a source image and text prompt
View Documentation →
Gemini Flash Image
Fast photoreal image generation - 14 credits per image
View Documentation →
GLM Image
Posters and clean graphic compositions - 2 credits per image
View Documentation →
Auto Image
Routes across premium models for the best result - 21 credits per image
View Documentation →
🎬 WAN Video Generator
Transform images into dynamic videos with AI
View Documentation →
🎥 LTXV Video Generator
Simple, cost-effective image animations
View Documentation →
🚀 RA2V Smart Generator
Intelligent video generation with auto backend selection
View Documentation →
Authentication
All API requests require your API key. Get yours from your account settings, where you can also create separate keys per app and revoke them at any time. Send it as Authorization: Bearer YOUR_API_KEY or X-API-Key: YOUR_API_KEY. Keys are scoped to the site that issued them.
Chat with a Character
Send an exact character name or URL name. Netwrck loads that character's description and greeting automatically. Pass prior turns in context when you manage conversation history outside Netwrck.
curl -X POST https://netwrck.com/api/chatpred_or \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"character": "Sherlock Holmes",
"query": "What do you notice about this room?",
"model_name": "deepseek/deepseek-v4-flash",
"use_usage_credits": true
}'
| Field | Required | Description |
|---|---|---|
query | Yes | The user's message. |
character | Yes | Exact character name or URL name. |
model_name | No | Model ID from the model catalog. |
context | No | Conversation history or additional instructions. When supplied, it overrides automatic character context. |
use_usage_credits | No | Charge API credits for this chat request. |
Pricing
| API | Cost | Description |
|---|---|---|
| LLM and Character Chat | From $0.072 input / $0.072 output per 1M tokens | Direct token pricing by selected model |
| RA1 Art Generator | $0.04 per image | High-quality AI image generation |
| RA2 Art Generator | $0.04 per image (4 credits) | High-quality AI image generation |
| RA2 Image Editor | $0.04 per edit (4 credits) | AI image editing from a source image |
| WAN 2.2 Video Generator | $0.30 per video | Advanced video generation (flat rate) |
| LTXV Video Generator | $0.05 per video | Simple image-to-video animations |
| LTX 2 Video Generator | $0.072 per second (1080p) | High-fidelity image or text to video |
| RA2V Smart Generator | Variable | Auto-selects optimal backend |
| BiRefNet Background Remover | $0.02 per image | AI image background removal |
| BiRefNet Video BG Remover | $0.50 per video | AI video background removal |
| Failed requests | Free | No charge for failed generations |
Charges are processed through Stripe and deducted from your account balance.
Code Examples
import requests
import json
url = "https://netwrck.com/api/ra1"
api_key = "YOUR_API_KEY"
payload = {
"api_key": api_key,
"prompt": "A serene beach at sunset with palm trees",
"size": "1024x768",
"enable_safety_checker": True
}
headers = {
"Content-Type": "application/json"
}
response = requests.post(url, headers=headers, json=payload)
if response.status_code == 200:
result = response.json()
print(f"Image generated successfully!")
print(f"Image URL: {result['image_url']}")
print(f"Request ID: {result['request_id']}")
else:
print(f"Error: {response.status_code}")
print(response.text)
// Using fetch API
const url = 'https://netwrck.com/api/ra1';
const apiKey = 'YOUR_API_KEY';
const payload = {
api_key: apiKey,
prompt: 'A majestic mountain landscape with a waterfall',
size: '1024x1024',
enable_safety_checker: true
};
fetch(url, {
method: 'POST',
headers: {
'Content-Type': 'application/json'
},
body: JSON.stringify(payload)
})
.then(response => {
if (!response.ok) {
throw new Error(`HTTP error! Status: ${response.status}`);
}
return response.json();
})
.then(data => {
console.log('Image generated successfully!');
console.log('Image URL:', data.image_url);
console.log('Request ID:', data.request_id);
})
.catch(error => {
console.error('Error:', error);
});
const axios = require('axios');
const url = 'https://netwrck.com/api/ra1';
const apiKey = 'YOUR_API_KEY';
const payload = {
api_key: apiKey,
prompt: 'Abstract digital art with swirling colors',
size: '768x1024',
enable_safety_checker: true
};
axios.post(url, payload, {
headers: {
'Content-Type': 'application/json'
}
})
.then(response => {
console.log('Image generated successfully!');
console.log('Image URL:', response.data.image_url);
console.log('Request ID:', response.data.request_id);
})
.catch(error => {
console.error('Error:', error.response ? error.response.data : error.message);
});
curl -X POST \
https://netwrck.com/api/ra1 \
-H 'Content-Type: application/json' \
-d '{
"api_key": "YOUR_API_KEY",
"prompt": "A cyberpunk street scene with rain and neon signs",
"size": "1024x768",
"enable_safety_checker": true
}'
<?php
$url = 'https://netwrck.com/api/ra1';
$api_key = 'YOUR_API_KEY';
$payload = array(
'api_key' => $api_key,
'prompt' => 'A fantasy castle on a floating island in the sky',
'size' => '1024x1024',
'enable_safety_checker' => true
);
$options = array(
'http' => array(
'header' => "Content-type: application/json\r\n",
'method' => 'POST',
'content' => json_encode($payload)
)
);
$context = stream_context_create($options);
$response = file_get_contents($url, false, $context);
if ($response !== false) {
$result = json_decode($response, true);
echo "Image generated successfully!\n";
echo "Image URL: " . $result['image_url'] . "\n";
echo "Request ID: " . $result['request_id'] . "\n";
} else {
echo "Error generating image\n";
}
?>
Netwrck