Image Generation API

Generate stunning visuals from text descriptions using advanced models like DALL-E 3 and Fal-AI Flux. Unified access via a single, standard completions interface.

01Request Parameters

Image Properties

sizestring

Image dimensions (e.g., '1024x1024', '1024x1792').

qualitystring

Rendering quality ('standard' or 'hd').

numberinteger

Number of independent generations.

Text-to-Image Example

// Generate a detailed architectural render

{
  "provider": "openai",
  "model": "dall-e-3",
  "messages": [
    {
      "role": "user",
      "content": "A Bauhaus style villa in a lush forest, architectural photography."
    }
  ],
  "size": "1024x1024",
  "quality": "hd",
  "number": 1
}

02Response

{ "id": "img_12345abcde", "created": 1711468800, "images": [ { "url": "https://media.oneinfer.ai/i/gen_987.png", "revised_prompt": "A clean, Bauhaus-style villa..." } ], "provider": "openai", "model": "dall-e-3" }

Speech-to-Text (Transcriptions)

Supported Models

whisper-large-v3-turbo (Groq)
whisper-1 (OpenAI)

For transcription, standard Chat Completion JSON bodies are not used. Instead, use multipart/form-data to upload the audio file.

Error Status Codes

Code	Status	Description
200	OK	Audio generated or transcribed successfully.
400	Bad Request	Invalid request body or unsupported provider.
401	Unauthorized	Missing or invalid Authorization header / Bearer token.
403	Forbidden	Insufficient credit balance.
422	Unprocessable Entity	Request body failed schema validation.
500	Internal Server Error	Unexpected error during audio generation.