Skip to main content
TrueFoundry AI Gateway supports text-to-image generation capabilities from multiple providers. Users can send text prompts to generate corresponding images.

​
Supported Providers

  • OpenAI: gpt-image-1, dall-e-2, dall-e-3
  • Vertex AI:
    • Imagen 3.0/4.0 models: imagen-3.0-generate-002, imagen-3.0-generate-001, imagen-3.0-fast-generate-001, imagen-4.0-generate, imagen-4.0-fast-generate, imagen-4.0-ultra-generate
    • Gemini models: gemini-2.5-flash-image, gemini-3-pro-image-preview
  • Bedrock: Titan and Nova models (amazon.titan-image-generator-v1, amazon.titan-image-generator-v2, amazon.nova-canvas-v1-0) + Stability AI models
  • Azure OpenAI: gpt-image-1, dall-e-2, dall-e-3

​
Code Example

from openai import OpenAI
import base64

BASE_URL = "https://{controlPlaneUrl}/api/llm"
API_KEY = "your-truefoundry-api-key"

# Configure OpenAI client with TrueFoundry settings
client = OpenAI(
    api_key=API_KEY,
    base_url=BASE_URL,
)

try:
    response = client.images.generate(
        model="openai-main/dalle-e-2",
        prompt="A beautiful sunset over mountains",
        n=1,
        size="1024x1024"
    )

    # Handle URL response
    if hasattr(response.data[0], 'url') and response.data[0].url:
        print(f"Image URL: {response.data[0].url}")

    # Handle base64 response
    if hasattr(response.data[0], 'b64_json') and response.data[0].b64_json:
        image_bytes = base64.b64decode(response.data[0].b64_json)
        with open("generated_image.png", "wb") as f:
            f.write(image_bytes)
        print("Image saved as generated_image.png")

except Exception as e:
    print(f"Error: {e}")

​
Response Format

{
  "created": 1713833628,
  "data": [
    {
      "url": "...",
      "b64_json": "..."
    }
  ]
}