Image recognition

Use the chat completions API to describe or reason about images. Add both the prompt and the image URL to the same user message so the model can reference the visual context.

Image recognition uses chat completions with image input. To create or edit image outputs, use the Image generation and edits endpoints instead.

Streaming example

from openai import OpenAI

client = OpenAI(
    base_url="https://api.llm7.io/v1",
    api_key="unused",  # Use a https://dash.llm7.io/ token for higher limits.
)

image_url = "https://images.weserv.nl/?url=wsrv.nl/lichtenstein.jpg&w=600&output=webp"

messages = [
    {
        "role": "user",
        "content": [
            {"type": "text", "text": "Describe this image for alt text."},
            {"type": "image_url", "image_url": {"url": image_url}},
        ],
    }
]

stream = client.chat.completions.create(
    model="default",  # or a model ID with image input from /v1/models
    messages=messages,
    temperature=0.5,
    stream=True,
)

model_used = None
for chunk in stream:
    model_used = chunk.model
    delta = chunk.choices[0].delta.content or []
    if isinstance(delta, list):
        delta = "".join(
            part.get("text", "") for part in delta if part.get("type") == "text"
        )
    print(delta, end="", flush=True)

print(f"\nModel selected: {model_used}")

Use a publicly reachable https image (or a signed URL) and keep text + image together in one content array. Use the Models API to find models with image in modalities.input.

Non-streaming call

from openai import OpenAI

client = OpenAI(
    base_url="https://api.llm7.io/v1",
    api_key="unused",  # Use a https://dash.llm7.io/ token for higher limits.
)

image_url = "https://images.weserv.nl/?url=wsrv.nl/lichtenstein.jpg&w=600&output=webp"

result = client.chat.completions.create(
    model="pro",  # or a model ID with image input from /v1/models
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Summarize the scene in one sentence."},
                {"type": "image_url", "image_url": {"url": image_url}},
            ],
        }
    ],
    temperature=0.3,
)

print(result.choices[0].message.content)
print(f"Model selected: {result.model}")

What to remember

messages[*].content is an array: include both text and image_url parts in the same user message.
Image URLs must be reachable over HTTPS; signed URLs work if they stay valid for the request duration.
response.model (or chunk.model while streaming) tells you which underlying model handled the call.

Getting started

Text generation

Images

Videos

AI tools

Streaming example

Non-streaming call

What to remember

​Streaming example

​Non-streaming call

​What to remember

Streaming example

Non-streaming call

What to remember