Run any Vision Language Model with fal. Analyze and understand images using Claude (Anthropic), GPT-5 / GPT-4o (OpenAI), Gemini (Google), Grok (xAI), Llama (Meta), Qwen, Pixtral (Mistral), and more. Send one or multiple images for captioning, analysis, OCR, or visual Q&A. Powered by OpenRouter.

openrouter/router/vision

Inference

Commercial use

Streaming

Partner

Schema

Playground API Examples

Input

Prompt*

Additional Settings

Customize your input with more control.

Result

Idle

What would you like to do next?

openrouter/router/vision

Schema

Input

Prompt*

Additional Settings

Customize your input with more control.

Result

Idle

What would you like to do next?

Close-up, detailed shot of an Inuit man, 30s-40s, with warm brown eyes, a trimmed black beard and mustache, frosted with snow and ice, looking thoughtfully upwards, against a blurred background of a snowstorm and cold, pale blue sky, wearing a thick, faux fur-lined parka with light brown and white fur, covered in snow, with flakes of snow falling on his hair, beard, and parka, his skin has slight blemishes and small scars.

python

from openai import OpenAI
import os

client = OpenAI(
    base_url="https://fal.run/openrouter/router/openai/v1",
    api_key="not-needed",
    default_headers={
        "Authorization": f"Key {os.environ['FAL_KEY']}",
    },
)

response = client.chat.completions.create(
    model="google/gemini-2.5-flash",
    messages=[
        {
            "role": "system",
            "content": "Only answer the question, do not provide any additional information or add any prefix/suffix other than the answer of the original question. Don't use markdown.",
        },
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Caption this image for a text-to-image model with as much detail as possible."},
                {
                    "type": "image_url",
                    "image_url": "https://fal.media/files/tiger/4Ew1xYW6oZCs6STQVC7V8_86440216d0fe42e4b826d03a2121468e.jpg",
                },
            ],
        },
    ],
    temperature=1,
)

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

python

from openai import OpenAI
import os

client = OpenAI(
    base_url="https://fal.run/openrouter/router/openai/v1",
    api_key="not-needed",
    default_headers={
        "Authorization": f"Key {os.environ['FAL_KEY']}",
    },
)

stream = client.chat.completions.create(
    model="google/gemini-2.5-flash",
    messages=[
        {
            "role": "system",
            "content": "Only answer the question, do not provide any additional information or add any prefix/suffix other than the answer of the original question. Don't use markdown.",
        },
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Caption this image for a text-to-image model with as much detail as possible."},
                {
                    "type": "image_url",
                    "image_url": "https://fal.media/files/tiger/4Ew1xYW6oZCs6STQVC7V8_86440216d0fe42e4b826d03a2121468e.jpg",
                },
            ],
        },
    ],
    temperature=1,
    stream=True,
)

for chunk in stream:
    if chunk.choices and chunk.choices[0].delta:
        print(chunk.choices[0].delta.content, end="", flush=True)

python

from openai import OpenAI
import os

client = OpenAI(
    base_url="https://fal.run/openrouter/router/openai/v1",
    api_key="not-needed",
    default_headers={
        "Authorization": f"Key {os.environ['FAL_KEY']}",
    },
)

response = client.chat.completions.create(
    model="google/gemini-2.5-flash",
    messages=[
        {
            "role": "system",
            "content": "Only answer the question, do not provide any additional information or add any prefix/suffix other than the answer of the original question. Don't use markdown.",
        },
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Caption this image for a text-to-image model with as much detail as possible."},
                {
                    "type": "image_url",
                    "image_url": "https://fal.media/files/tiger/4Ew1xYW6oZCs6STQVC7V8_86440216d0fe42e4b826d03a2121468e.jpg",
                },
            ],
        },
    ],
    temperature=1,
)

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

python

from openai import OpenAI
import os

client = OpenAI(
    base_url="https://fal.run/openrouter/router/openai/v1",
    api_key="not-needed",
    default_headers={
        "Authorization": f"Key {os.environ['FAL_KEY']}",
    },
)

stream = client.chat.completions.create(
    model="google/gemini-2.5-flash",
    messages=[
        {
            "role": "system",
            "content": "Only answer the question, do not provide any additional information or add any prefix/suffix other than the answer of the original question. Don't use markdown.",
        },
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Caption this image for a text-to-image model with as much detail as possible."},
                {
                    "type": "image_url",
                    "image_url": "https://fal.media/files/tiger/4Ew1xYW6oZCs6STQVC7V8_86440216d0fe42e4b826d03a2121468e.jpg",
                },
            ],
        },
    ],
    temperature=1,
    stream=True,
)

for chunk in stream:
    if chunk.choices and chunk.choices[0].delta:
        print(chunk.choices[0].delta.content, end="", flush=True)

openrouter/router/vision

Input

Result

What would you like to do next?

Input

Result

What would you like to do next?

openrouter/router/vision

Input

Result

What would you like to do next?

Input

Result

What would you like to do next?

Input

Result

What would you like to do next?

Input

Result

What would you like to do next?

Input

Result

What would you like to do next?

🚀 Usage with OpenAI Client

🚿 Streaming Example

📚 Documentation

🚀 Usage with OpenAI Client

🚿 Streaming Example

📚 Documentation