docs/Getting Started
Multimodal & Vision Inputs
Send images, UI mockups, documents, and charts alongside text prompts.
Providing Image Content
Pass image content blocks inside the message `content` array. You can supply either a publicly accessible HTTPS URL or a Base64-encoded Data URI (`data:image/png;base64,...`).
Vision inputs are natively supported across **Claude Sonnet 5.5**, **Claude Opus 5.5**, **GPT-5**, **GPT-4.5 Omni**, and **Gemini 4 Argon**.
from openai import OpenAI
client = OpenAI(
base_url="https://unlockedai.net/v1",
api_key="<YOUR_UNLOCKED_API_KEY>",
)
response = client.chat.completions.create(
model="claude-sonnet-5.5",
messages=[
{
"role": "user",
"content": [
{"type": "text", "text": "What components and layout patterns are used here?"},
{
"type": "image_url",
"image_url": {
"url": "https://unlockedai.net/images/dashboard-mockup.png"
}
}
]
}
]
)
print(response.choices[0].message.content)Need an Unlocked AI Key or Credits?
Generate secret API keys backed by non-expiring pay-as-you-go credits starting at $5. No monthly minimums.