Skip to main content

Image Analysis & Generation

The RouteLLM API provides full image support — both analyzing images as input (vision) and generating images as output — all via the same unified /v1/chat/completions endpoint.

Image Analysis​

Send images alongside text to any vision-capable model for description, classification, OCR, comparison, and more. Images can be provided as an HTTPS URL or base64-encoded data.

Supported Input Formats​

  • PNG, JPEG, WebP, GIF
  • Images are automatically resized and processed by the API
  • Multiple images can be included in a single message

Providing Images as Input​

{
  "model": "route-llm",
  "messages": [
    {
      "role": "user",
      "content": [
        { "type": "text", "text": "Describe the image" },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://example.com/image.jpg"
          }
        }
      ]
    }
  ]
}

Note: Base64 images must use the data URI format: data:image/<format>;base64,<base64_string>

Image Generation​

The RouteLLM API supports image generation from text prompts using a wide range of state-of-the-art image generation models. Image generation uses the same unified chat completions endpoint as text generation, with additional modalities and image_config parameters.

Supported Models​

ModelDescription
flux_kontextContext-aware image generation
flux_kontext_editContext-aware image editing
flux_pro_ultraHighest quality FLUX generation
flux_proProfessional image generation
flux_pro_cannyEdge-guided image generation
flux_pro_depthDepth-guided image generation
flux2_proHigh-quality, photorealistic image generation
flux2Image generation

Request Parameters​

Image generation uses the same /v1/chat/completions endpoint as text generation.

model (string, required)​

The ID of the model to use. Can be any supported image generation model or a Gemini/OpenAI multimodal LLM.

messages (array, required)​

The conversation messages. The user's message should contain the image generation prompt.

{
  "role": "user",
  "content": "A beautiful sunset over mountains"
}

modalities (array, required for image generation)​

Must be set to ["image"] to generate images.

"modalities": ["image"]

image_config (object, optional)​

Configuration for image generation. Parameters vary by model.

Common Parameters​

The following parameters are supported by most image generation models:

ParameterTypeRequiredDescriptionValid ValuesDefault
promptstringYesDescribe the scene or action to generateAny text—
num_imagesintegerNoNumber of images to generate1–41
rewrite_promptbooleanNoAutomatically improve the prompt for better resultstrue, falsetrue

Note: num_images is not supported by flux_kontext_edit, gpt_image15_edit, imagine_art, magnific, and midjourney.

Model-Specific Parameters​

Model ID: flux_pro

ParameterTypeRequiredDescriptionValid ValuesDefault
sizestringNoResolution of the generated image1440x1440, 1440x1024, 1024x1440, 1440x768, 768x1440, 1024x1024, 1024x768, 768x1024, 768x576, 576x768, 640x640, 768x448, 448x768, 640x480, 480x6401440x1440
seednumberNoSeed for reproducible resultsAny integer—

Response Schema​

Image generation responses follow the same unified chat completion format. When modalities includes "image", the response contains image URLs in the images field of the message.

{
  "created": 1677858242,
  "model": "gemini-2.5-pro",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "",
        "images": [
          {
            "type": "image_url",
            "image_url": {
              "url": "https://example.com/generated-image-1.png"
            }
          },
          {
            "type": "image_url",
            "image_url": {
              "url": "https://example.com/generated-image-2.png"
            }
          }
        ]
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "compute_points_used": 150
  }
}

Code Examples​

1. Basic Image Generation​

from openai import OpenAI

client = OpenAI(
    base_url="<your base url>",
    api_key="<your_api_key>",
)

response = client.chat.completions.create(
    model="gemini-2.5-pro",
    messages=[
        {
            "role": "user",
            "content": "A beautiful sunset over mountains"
        }
    ],
    modalities=["image"],
    image_config={
        "num_images": 1
    }
)

for image in response.choices[0].message.images:
    if image['type'] == "image_url":
        print(f"Generated image: {image['image_url']['url']}")

2. Multiple Images​

from openai import OpenAI

client = OpenAI(
    base_url="<your base url>",
    api_key="<your_api_key>",
)

response = client.chat.completions.create(
    model="flux2_pro",  # use GET /v1/models for exact model IDs
    messages=[
        {
            "role": "user",
            "content": "A futuristic cityscape at night with neon lights and flying cars"
        }
    ],
    modalities=["image"],
    image_config={
        "num_images": 3,
        "aspect_ratio": "1:1"
    }
)

image_urls = [
    item['image_url']['url']
    for item in response.choices[0].message.images
    if item['type'] == "image_url"
]
for idx, url in enumerate(image_urls, 1):
    print(f"Image {idx}: {url}")

3. Portrait Orientation​

from openai import OpenAI

client = OpenAI(
    base_url="<your base url>",
    api_key="<your_api_key>",
)

response = client.chat.completions.create(
    model="flux2_pro",
    messages=[
        {
            "role": "user",
            "content": "A full-body portrait of a fashion model in elegant evening wear"
        }
    ],
    modalities=["image"],
    image_config={
        "num_images": 1,
        "aspect_ratio": "2:3"
    }
)

for image in response.choices[0].message.images:
    if image['type'] == "image_url":
        print(f"Portrait image: {image['image_url']['url']}")

4. OpenAI Model with Quality Control​

from openai import OpenAI

client = OpenAI(
    base_url="<your base url>",
    api_key="<your_api_key>",
)

response = client.chat.completions.create(
    model="gpt-5.1",
    messages=[
        {
            "role": "user",
            "content": "A whimsical illustration of a magical forest with glowing mushrooms"
        }
    ],
    modalities=["image"],
    image_config={
        "num_images": 1,
        "aspect_ratio": "1:1",
        "quality": "high"
    }
)

for image in response.choices[0].message.images:
    if image['type'] == "image_url":
        print(f"Image URL: {image['image_url']['url']}")

5. Gemini Model with Image Size and Resolution​

from openai import OpenAI

client = OpenAI(
    base_url="<your base url>",
    api_key="<your_api_key>",
)

response = client.chat.completions.create(
    model="nano_banana2",
    messages=[
        {
            "role": "user",
            "content": "A professional headshot of a business executive"
        }
    ],
    modalities=["image"],
    image_config={
        "num_images": 1,
        "aspect_ratio": "2:3",
        "resolution": "2K"
    }
)

for image in response.choices[0].message.images:
    if image['type'] == "image_url":
        print(f"Image URL: {image['image_url']['url']}")