POST /openai/chat/completions
Generate text using OpenAI-compatible chat models like GPT-4, Claude-3, and Gemini Pro.
| Parameter | Type | Req | Description | Example |
|---|---|---|---|---|
| model | string | required | Model ID (e.g., gpt-4-turbo, claude-3-sonnet, gemini-pro) | gpt-4-turbo |
| messages | array | required | List of role/content objects | [{role:'user',content:'Hi'}] |
| temperature | number | optional | Determinism vs creativity (0–2) | 0.7 |
| top_p | number | optional | Nucleus sampling (0–1) | 1 |
| max_tokens | number | optional | Max tokens to generate | 1024 |
| stream | boolean | optional | Stream response in chunks | false |
| stop | array | optional | Stop sequences | ['\n', 'END'] |
{
"model": "gpt-4-turbo",
"messages": [{"role": "user", "content": "Hello"}],
"temperature": 0.7,
"max_tokens": 1024,
"stream": false
}POST /openai/images/generations
Generate high-quality images from text descriptions using DALL-E 3.
| Parameter | Type | Req | Description | Example |
|---|---|---|---|---|
| model | string | required | Model ID | dall-e-3 |
| prompt | string | required | Text description of the image (max 1000 chars) | A cozy cabin… |
| size | enum | optional | Image size | 1024x1024 | 1792x1024 | 1024x1792 |
| quality | enum | optional | Quality tier | standard | hd |
| style | enum | optional | Style preference | natural | vivid |
| n | number | optional | Number of images (max 1 for dall-e-3) | 1 |
{
"model": "dall-e-3",
"prompt": "A cozy cabin in the woods at sunset, photorealistic style",
"size": "1024x1024",
"quality": "standard",
"style": "natural",
"n": 1
}POST /google/nano-banana
Edit images using Google's Nano Banana model with text prompts.
| Parameter | Type | Req | Description | Example |
|---|---|---|---|---|
| prompt | string | required | Text description of desired changes | Make the sheets blue |
| image | string | required | Base64 encoded input image | data:image/jpeg;base64,... |
{
"prompt": "Make the sheets in the style of the logo. Make the scene natural.",
"image": "base64_encoded_image_data"
}POST /runway/generate
Generate videos from text prompts or images using Runway's Gen-3 model.
| Parameter | Type | Req | Description | Example |
|---|---|---|---|---|
| model | string | required | Model ID | runway-gen3 |
| mode | enum | required | Generation mode | text_to_video | image_to_video |
| prompt | string | required | Video description or style | Aerial shot over ocean |
| image_url | string | conditional | Source image for image_to_video mode | https://…/input.png |
| duration | number | optional | Video length in seconds | 4 | 8 | 16 |
| resolution | enum | optional | Output resolution | 768x768 | 1280x768 | 768x1280 |
| seed | number | optional | Deterministic seed for reproducibility | 42 |
{
"model": "runway-gen3",
"mode": "text_to_video",
"prompt": "Aerial shot over ocean at golden hour, cinematic",
"duration": 8,
"resolution": "1280x768",
"seed": 42
}POST /elevenlabs/tts
Convert text to natural-sounding speech using ElevenLabs voices.
| Parameter | Type | Req | Description | Example |
|---|---|---|---|---|
| text | string | required | Text to synthesize (max 2500 chars) | Hello from Core API |
| voice_id | string | required | Voice identifier | rachel | adam | sam | etc. |
| model_id | string | optional | TTS model version | eleven_monolingual_v1 |
| voice_settings | object | optional | Voice stability and similarity | {stability: 0.75} |
{
"text": "Hello from Core API, this is a test of speech synthesis.",
"voice_id": "rachel",
"model_id": "eleven_monolingual_v1",
"voice_settings": {
"stability": 0.75,
"similarity_boost": 0.75
}
}POST /azure/speech
Convert text to speech using Microsoft Azure's neural voices with SSML support.
| Parameter | Type | Req | Description | Example |
|---|---|---|---|---|
| text | string | required | Text to synthesize | Welcome to Core API |
| voice | string | required | Azure neural voice ID | en-US-JennyNeural |
| style | string | optional | Speaking style | general | cheerful | sad |
| rate | number | optional | Speech rate (-50 to 50) | 0 |
| pitch | number | optional | Voice pitch (-50 to 50) | 0 |
{
"text": "Welcome to Core API, your unified AI platform",
"voice": "en-US-JennyNeural",
"style": "cheerful",
"rate": 0,
"pitch": 5
}200 - Success400 - Bad Request (invalid parameters)401 - Unauthorized (invalid API key)429 - Rate limit exceeded500 - Server error (retry with backoff)Mori API is an AI model aggregation platform that gives developers a single, unified API to access 50+ AI models across text, image, audio, and video — with transparent pricing, real‑time analytics, and enterprise‑grade reliability.
