API Reference - Mollyra AI | Developer Documentation

Authentication

All API requests require an API key. Include your API key in the Authorization header of every request.


curl https://api.mollyra.ai/v1/chat/completions \

  -H "Authorization: Bearer YOUR_API_KEY" \

  -H "Content-Type: application/json"


# Python

import requests


headers = {

    "Authorization": "Bearer YOUR_API_KEY",

    "Content-Type": "application/json"

}

Chat Completions

Create chat-based completions using our advanced language models. Supports streaming, system messages, and multi-turn conversations.

POST /v1/chat/completions

Request Body

Parameter	Type	Description
modelrequired	string	The model to use (gpt-4-turbo, claude-3-opus, mollyra-x)
messagesrequired	array	Array of message objects with role and content
temperatureoptional	number	Sampling temperature (0-2). Default: 0.7
max_tokensoptional	integer	Maximum tokens to generate. Default: 2048
streamoptional	boolean	Enable streaming responses. Default: false


{

  "model": "gpt-4-turbo",

  "messages": [

    {"role": "system", "content": "You are a helpful assistant."},

    {"role": "user", "content": "Hello!"}

  ],

  "temperature": 0.7,

  "max_tokens": 1000

}

Response


{

  "id": "chatcmpl-123",

  "object": "chat.completion",

  "created": 1677652288,

  "model": "gpt-4-turbo",

  "choices": [{

    "index": 0,

    "message": {

      "role": "assistant",

      "content": "Hello! How can I help you today?"

    },

    "finish_reason": "stop"

  }],

  "usage": {"prompt_tokens": 20, "completion_tokens": 10, "total_tokens": 30}

}

Image Generation

Generate images from text prompts using DALL-E 3 and our custom diffusion models.

POST /v1/images/generations

Request Body

Parameter	Type	Description
promptrequired	string	Text description of the desired image
modeloptional	string	Image model to use (dall-e-3, mollyra-diffusion). Default: dall-e-3
noptional	integer	Number of images to generate (1-10). Default: 1
sizeoptional	string	Image size (1024x1024, 1792x1024, 1024x1792)


{

  "prompt": "A futuristic cyberpunk city with neon lights, purple and cyan color scheme",

  "model": "dall-e-3",

  "n": 1,

  "size": "1024x1024"

}

Embeddings

Generate vector embeddings for text, useful for semantic search, clustering, and similarity matching.

POST /v1/embeddings

Parameter	Type	Description
inputrequired	string or array	Text to embed
modeloptional	string	Embedding model (text-embedding-3-small, text-embedding-3-large)

Available Models

Model	Type	Context Window	Best For
gpt-4-turbo	Chat	128K tokens	Complex reasoning, coding
gpt-3.5-turbo	Chat	16K tokens	Fast responses, cost efficiency
claude-3-opus	Chat	200K tokens	Long documents, analysis
claude-3-sonnet	Chat	200K tokens	Balanced performance
mollyra-x	Chat	32K tokens	Specialized tasks
dall-e-3	Image	-	High-quality images

Rate Limits

Rate limits vary by plan. Upgrade to Enterprise for higher limits.

Plan	Requests/minute	Tokens/minute
Free	20	10,000
Pro	500	500,000
Enterprise	Custom	Custom

Error Handling

Our API uses standard HTTP status codes. Error responses include a JSON body with details.

Code	Meaning
400	Bad Request - Invalid parameters
401	Unauthorized - Invalid API key
403	Forbidden - Insufficient permissions
429	Too Many Requests - Rate limit exceeded
500	Server Error - Something went wrong on our end

Official SDKs

Official SDKs are available for popular programming languages.

Python

pip install mollyra

Node.js

npm install mollyra-sdk

Go

go get github.com/mollyra/sdk

Ruby

gem install mollyra