"Multimodal AI API Guide 2026: Vision, Audio & Video in One Platform"

from openai import OpenAI

# Access all multimodal models through one API
client = OpenAI(
    api_key="your-api-key",
    base_url="https://api.crazyrouter.com/v1"
)

# Analyze an image
response = client.chat.completions.create(
    model="gpt-5",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Describe this image in detail. What architecture patterns do you see?"},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://example.com/system-diagram.png",
                        "detail": "high"  # "auto", "low", or "high"
                    }
                }
            ]
        }
    ],
    max_tokens=1024
)

print(response.choices[0].message.content)

# Compare two images
response = client.chat.completions.create(
    model="gemini-3-pro",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Compare these two UI designs. Which is better for mobile?"},
                {"type": "image_url", "image_url": {"url": "https://example.com/design-a.png"}},
                {"type": "image_url", "image_url": {"url": "https://example.com/design-b.png"}}
            ]
        }
    ]
)

import base64

# Read local image file
with open("screenshot.png", "rb") as f:
    image_data = base64.b64encode(f.read()).decode("utf-8")

response = client.chat.completions.create(
    model="claude-opus-4-6",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Extract all text from this screenshot."},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": f"data:image/png;base64,{image_data}"
                    }
                }
            ]
        }
    ]
)

# Generate images with DALL-E 3
response = client.images.generate(
    model="dall-e-3",
    prompt="A futuristic city skyline at sunset, cyberpunk style, ultra detailed",
    size="1024x1024",
    quality="hd",
    n=1
)

image_url = response.data[0].url
print(f"Image URL: {image_url}")

# Access Midjourney through Crazyrouter's unified API
response = client.images.generate(
    model="midjourney",
    prompt="A serene Japanese garden with cherry blossoms, watercolor painting style --ar 16:9 --v 7",
    size="1024x1024",
    n=1
)

# Transcribe audio with Whisper
with open("meeting.mp3", "rb") as audio_file:
    transcript = client.audio.transcriptions.create(
        model="whisper-1",
        file=audio_file,
        response_format="verbose_json",
        timestamp_granularities=["segment"]
    )

for segment in transcript.segments:
    print(f"[{segment['start']:.1f}s] {segment['text']}")

# Generate natural speech
speech = client.audio.speech.create(
    model="tts-1-hd",
    voice="nova",
    input="Welcome to the multimodal AI era."
)

speech.stream_to_file("welcome.mp3")

import google.generativeai as genai

# Gemini 3 Pro can analyze video directly
# Upload a video file first
video_file = genai.upload_file("product_demo.mp4")

model = genai.GenerativeModel("gemini-3-pro")
response = model.generate_content([
    "Summarize this product demo video. List the key features shown.",
    video_file
])

print(response.text)

import requests

# Generate video via Crazyrouter
response = requests.post(
    "https://api.crazyrouter.com/v1/videos/generations",
    headers={
        "Authorization": "Bearer your-api-key",
        "Content-Type": "application/json"
    },
    json={
        "model": "sora-2",
        "prompt": "A golden retriever playing in autumn leaves, slow motion, cinematic",
        "duration": 5,
        "resolution": "1080p"
    }
)

video_url = response.json()["data"][0]["url"]
print(f"Video: {video_url}")

from openai import OpenAI

client = OpenAI(
    api_key="your-api-key",
    base_url="https://api.crazyrouter.com/v1"
)

class MultimodalAssistant:
    def __init__(self):
        self.conversation = []
    
    def analyze_image(self, image_path: str, question: str) -> str:
        """Analyze an image with a question"""
        import base64
        with open(image_path, "rb") as f:
            img_b64 = base64.b64encode(f.read()).decode()
        
        response = client.chat.completions.create(
            model="gpt-5",
            messages=[{
                "role": "user",
                "content": [
                    {"type": "text", "text": question},
                    {"type": "image_url", "image_url": {"url": f"data:image/png;base64,{img_b64}"}}
                ]
            }]
        )
        return response.choices[0].message.content
    
    def transcribe_audio(self, audio_path: str) -> str:
        """Transcribe audio to text"""
        with open(audio_path, "rb") as f:
            result = client.audio.transcriptions.create(
                model="whisper-1", file=f
            )
        return result.text
    
    def speak(self, text: str, output_path: str = "output.mp3"):
        """Convert text to speech"""
        speech = client.audio.speech.create(
            model="tts-1-hd", voice="nova", input=text
        )
        speech.stream_to_file(output_path)
    
    def generate_image(self, prompt: str) -> str:
        """Generate an image from description"""
        response = client.images.generate(
            model="dall-e-3", prompt=prompt,
            size="1024x1024", quality="hd"
        )
        return response.data[0].url

# Usage
assistant = MultimodalAssistant()

# Analyze a document image
text = assistant.analyze_image("document.png", "Extract the key data points from this chart")

# Convert analysis to speech
assistant.speak(text, "analysis.mp3")

# Generate a visualization
image_url = assistant.generate_image(f"An infographic showing: {text[:200]}")

try:
    response = client.chat.completions.create(
        model="gpt-5",
        messages=[{
            "role": "user",
            "content": [
                {"type": "text", "text": "Describe this image"},
                {"type": "image_url", "image_url": {"url": image_url}}
            ]
        }]
    )
except Exception as e:
    # Fallback to text-only model
    response = client.chat.completions.create(
        model="gpt-5-mini",
        messages=[{"role": "user", "content": "Image analysis unavailable. Please describe the image manually."}]
    )