Name: Llama 3.2 Vision 11B Image Captioning and Visual Q&A API
Brand: magicapi
SKU: api-magicapi-vision-ai-image-captioning-lucataco-ollama-llama3-2-vision-11b
Availability: InStock
Author: API Market

Shashank Agarwal

# 👁️ Image Captioning and Visual Q&A API (Meta Llama 3.2 Vision 11B)

## Overview
Llama 3.2 Vision 11B is a multimodal language model from Meta that reads an image and a text prompt and answers in text. This listing runs it with Ollama, packaged by lucataco.

Send an `image` URL and a `prompt`, for example "Describe this image in detail." or a question about the picture. The output is a list of text chunks; join them to get the full answer.

## Features
- **Image description**: detailed captions of photos, screenshots and illustrations.
- **Visual questions**: ask anything about the image in `prompt`.
- **Answer length**: `max_tokens` (default 512, minimum 1) caps the length of the answer.
- **Sampling controls**: `temperature` (0 to 1, default 0.7) and `top_p` (0 to 1, default 0.95).

## Use Cases
1. **Alt text**: describe images for accessibility and SEO.
2. **Catalog descriptions**: write first drafts of product or listing descriptions from photos.
3. **Content tagging**: describe what an image shows for search and moderation queues.
4. **Visual Q&A**: answer questions about a chart, scene or object in a picture.

## Visual Examples
### Example Input
![Example input image for Llama 3.2 Vision 11B](https://blog.api.market/wp-content/uploads/2026/10/rmgb-input-api-market.jpg)

Prompt: "Describe this image in detail."

Settings: `max_tokens` 512, `temperature` 0.7, `top_p` 0.95.

### Example Output
The model returned a list of text chunks. Joined, they read:

> This image depicts a striking scene of two giraffes standing together amidst a savannah-like landscape.
>
> In the foreground, one giraffe stands slightly behind and to the left of its companion, while the other is centered with its head turned towards the camera. All four legs are visible on both animals, displaying their long and slender proportions. The giraffes' distinctive brown coats feature dark spots scattered across them, adding to their unique appearance.
>
> The surrounding landscape is characterized by a mix of tall, dry grass and shrubs, which appear yellowish in color due to the fading light. Behind the pair of giraffes, several zebras can be seen grazing in the distance, while a lone tree stands off in the far left corner of the image. The sky above is a pale blue-gray hue, suggesting an overcast or cloudy day.
>
> The overall atmosphere of the image suggests that it was taken during late afternoon or early evening, as indicated by the warm tones and soft light cast upon the subjects.

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `image` | string (URL) | Yes |  |  | Input image for the model (jpeg, png, gif or webp). |
| `prompt` | string | Yes |  |  | Input text for the model, for example an instruction or a question about the image. |
| `max_tokens` | integer | No | `512` | 1 or more | Maximum number of tokens to generate. |
| `temperature` | number | No | `0.7` | 0 to 1 | Controls randomness. Lower values make the output more deterministic, higher values make it more random. |
| `top_p` | number | No | `0.95` | 0 to 1 | Controls diversity. Lower values make the output more focused, higher values make it more diverse. |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.011 per API unit.
- **1 API unit = 1 request with up to 9 seconds of processing.** A request that runs longer is billed one more unit for each started 9-second block (for example, more than 9 and up to 18 seconds of processing is 2 units, $0.022).
- Longer answers (a higher `max_tokens`) take longer and can use more units.
- **Example cost**: the example request (`max_tokens` 512) took 5.2 seconds of processing, which fits in one 9-second block: 1 API unit, $0.011.
- **Failed or cancelled predictions are not billed.**
- **GET requests to check prediction status** are free and don't count toward API unit usage.
- **No monthly subscription fee.**

## API Documentation

### Base URL
All API requests go to: `https://prod.api.market/api/v1/magicapi/vision-ai-image-captioning-lucataco-ollama-llama3-2-vision-11b`

### Authentication
Send your api.market API key in the `x-api-market-key` header:
```
x-api-market-key: YOUR_API_MARKET_KEY
```

### Asynchronous Processing
**IMPORTANT**: This API is asynchronous. The flow is:
1. Send a POST request to `/predictions`. A successful request returns **201 Created** with a prediction `id` and a `status` of `starting` or `processing`.
2. Poll GET `/predictions/{id}` with that ID.
3. Keep polling while `status` is `starting` or `processing`.
4. Stop when `status` is `succeeded` (read `output`), `failed` or `canceled` (read `error`).

A polling interval of 1 second and an overall timeout of 600 seconds (10 minutes) work well.

### Endpoints

#### Create a Prediction
```bash
curl -X POST "https://prod.api.market/api/v1/magicapi/vision-ai-image-captioning-lucataco-ollama-llama3-2-vision-11b/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "d4e81fc1472556464f1ee5cea4de177b2fe95a6eaadb5f63335df1ba654597af",
    "input": {
      "image": "https://blog.api.market/wp-content/uploads/2026/10/rmgb-input-api-market.jpg",
      "top_p": 0.95,
      "prompt": "Describe this image in detail.",
      "max_tokens": 512,
      "temperature": 0.7
    }
  }'
```

Response (201 Created):
```json
{
  "id": "n0p97hxg6hrmy0d1f1m9bjzvnr",
  "version": "d4e81fc1472556464f1ee5cea4de177b2fe95a6eaadb5f63335df1ba654597af",
  "status": "starting",
  "created_at": "2026-10-26T13:31:29.349Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/vision-ai-image-captioning-lucataco-ollama-llama3-2-vision-11b/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "n0p97hxg6hrmy0d1f1m9bjzvnr",
  "status": "succeeded",
  "output": [
    "This",
    " image",
    " depicts",
    " a",
    " striking",
    " scene",
    " of",
    " two",
    " gir",
    "aff",
    "es",
    " standing",
    " together",
    " amidst",
    " a",
    " sav",
    "annah",
    "-like",
    " landscape",
    ".\n\n",
    "In",
    " the",
    " foreground",
    ",",
    " one",
    " gir",
    "affe",
    " stands",
    " slightly",
    " behind",
    " and",
    " to",
    " the",
    " left",
    " of",
    " its",
    " companion",
    ",",
    " while",
    " the",
    " other",
    " is",
    " centered",
    " with",
    " its",
    " head",
    " turned",
    " towards",
    " the",
    " camera",
    ".",
    " All",
    " four",
    " legs",
    " are",
    " visible",
    " on",
    " both",
    " animals",
    ",",
    " displaying",
    " their",
    " long",
    " and",
    " slender",
    " proportions",
    ".",
    " The",
    " gir",
    "aff",
    "es",
    "'",
    " distinctive",
    " brown",
    " coats",
    " feature",
    " dark",
    " spots",
    " scattered",
    " across",
    " them",
    ",",
    " adding",
    " to",
    " their",
    " unique",
    " appearance",
    ".\n\n",
    "The",
    " surrounding",
    " landscape",
    " is",
    " characterized",
    " by",
    " a",
    " mix",
    " of",
    " tall",
    ",",
    " dry",
    " grass",
    " and",
    " shr",
    "ubs",
    ",",
    " which",
    " appear",
    " yellow",
    "ish",
    " in",
    " color",
    " due",
    " to",
    " the",
    " fading",
    " light",
    ".",
    " Behind",
    " the",
    " pair",
    " of",
    " gir",
    "aff",
    "es",
    ",",
    " several",
    " ze",
    "bras",
    " can",
    " be",
    " seen",
    " grazing",
    " in",
    " the",
    " distance",
    ",",
    " while",
    " a",
    " lone",
    " tree",
    " stands",
    " off",
    " in",
    " the",
    " far",
    " left",
    " corner",
    " of",
    " the",
    " image",
    ".",
    " The",
    " sky",
    " above",
    " is",
    " a",
    " pale",
    " blue",
    "-gray",
    " hue",
    ",",
    " suggesting",
    " an",
    " over",
    "cast",
    " or",
    " cloudy",
    " day",
    ".\n\n",
    "The",
    " overall",
    " atmosphere",
    " of",
    " the",
    " image",
    " suggests",
    " that",
    " it",
    " was",
    " taken",
    " during",
    " late",
    " afternoon",
    " or",
    " early",
    " evening",
    ",",
    " as",
    " indicated",
    " by",
    " the",
    " warm",
    " tones",
    " and",
    " soft",
    " light",
    " cast",
    " upon",
    " the",
    " subjects",
    ".",
    ""
  ],
  "error": null,
  "created_at": "2026-10-26T13:31:29.349Z",
  "started_at": "2026-10-26T13:32:06.394Z",
  "completed_at": "2026-10-26T13:32:11.639Z"
}
```

`output` is an array of text chunks. Join them without a separator to get the full answer.

### Status Codes
- **201 Created**: prediction created (POST `/predictions`). This is the normal success response.
- **200 OK**: prediction details returned (GET `/predictions/{id}`).
- **400 Bad Request**: invalid input, for example a missing `image` or `prompt`, or a `temperature` above 1.
- **401 Unauthorized**: missing or invalid API key.
- **404 Not Found**: no prediction with that ID.
- **429 Too Many Requests**: rate limit exceeded.
- **500 Internal Server Error** or **503 Service Unavailable**: temporary server problem; retry later.

## Rate Limits
Requests are rate limited to keep usage fair. If you receive a 429 response, wait and retry with exponential backoff.

## Error Handling
- Check the HTTP status code of every request and read the response body for the error message.
- A prediction can also end with `status` set to `failed`; the `error` field then explains why. Failed predictions are not billed.
- Retry 429, 500 and 503 responses with exponential backoff. Fix the input before retrying a 400.

## Implementation Guide
### Example Code

#### JavaScript
```javascript
const apiKey = "YOUR_API_MARKET_KEY";
const baseUrl = "https://prod.api.market/api/v1/magicapi/vision-ai-image-captioning-lucataco-ollama-llama3-2-vision-11b";

async function createAndWaitForPrediction(input) {
  const response = await fetch(`${baseUrl}/predictions`, {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "x-api-market-key": apiKey
    },
    body: JSON.stringify({ version: "d4e81fc1472556464f1ee5cea4de177b2fe95a6eaadb5f63335df1ba654597af", input })
  });

  if (response.status !== 201) {
    throw new Error(`API error: ${response.status} ${await response.text()}`);
  }

  const prediction = await response.json();
  return pollForResults(prediction.id);
}

const delay = (ms) => new Promise((resolve) => setTimeout(resolve, ms));

async function pollForResults(predictionId) {
  const maxTimeout = 600000;
  const pollInterval = 1000;
  const startTime = Date.now();

  while (Date.now() - startTime < maxTimeout) {
    const response = await fetch(`${baseUrl}/predictions/${predictionId}`, {
      headers: { "x-api-market-key": apiKey }
    });

    if (!response.ok) {
      throw new Error(`API error: ${response.status} ${await response.text()}`);
    }

    const prediction = await response.json();

    if (prediction.status === "succeeded") {
      return prediction.output.join("");
    }

    if (prediction.status === "failed" || prediction.status === "canceled") {
      throw new Error(`Prediction ${prediction.status}: ${prediction.error || "Unknown error"}`);
    }

    await delay(pollInterval);
  }

  throw new Error("Prediction timed out after 10 minutes");
}

createAndWaitForPrediction({
  "image": "https://blog.api.market/wp-content/uploads/2026/10/rmgb-input-api-market.jpg",
  "top_p": 0.95,
  "prompt": "Describe this image in detail.",
  "max_tokens": 512,
  "temperature": 0.7
}).then((output) => console.log(output));
```

#### Python
```python
import time
import requests

API_KEY = "YOUR_API_MARKET_KEY"
BASE_URL = "https://prod.api.market/api/v1/magicapi/vision-ai-image-captioning-lucataco-ollama-llama3-2-vision-11b"


def create_and_wait_for_prediction(input_data):
    headers = {"Content-Type": "application/json", "x-api-market-key": API_KEY}
    response = requests.post(
        f"{BASE_URL}/predictions",
        headers=headers,
        json={"version": "d4e81fc1472556464f1ee5cea4de177b2fe95a6eaadb5f63335df1ba654597af", "input": input_data},
    )

    if response.status_code != 201:
        raise Exception(f"API error: {response.status_code} {response.text}")

    return poll_for_results(response.json()["id"])


def poll_for_results(prediction_id):
    max_timeout = 600
    poll_interval = 1
    headers = {"x-api-market-key": API_KEY}
    start_time = time.time()

    while time.time() - start_time < max_timeout:
        response = requests.get(f"{BASE_URL}/predictions/{prediction_id}", headers=headers)

        if response.status_code != 200:
            raise Exception(f"API error: {response.status_code} {response.text}")

        prediction = response.json()

        if prediction["status"] == "succeeded":
            return "".join(prediction["output"])

        if prediction["status"] in ("failed", "canceled"):
            raise Exception(f"Prediction {prediction['status']}: {prediction.get('error') or 'Unknown error'}")

        time.sleep(poll_interval)

    raise Exception("Prediction timed out after 10 minutes")


print(create_and_wait_for_prediction({
    "image": "https://blog.api.market/wp-content/uploads/2026/10/rmgb-input-api-market.jpg",
    "top_p": 0.95,
    "prompt": "Describe this image in detail.",
    "max_tokens": 512,
    "temperature": 0.7
}))
```

## FAQ
- **Can I ask a question instead of asking for a description?**
  - Yes. Put any instruction or question about the image in `prompt`.
- **Why is the output a list?**
  - The model returns its answer as text chunks. Join them without a separator to get the full text.
- **How long can the answer be?**
  - Up to `max_tokens` tokens (default 512). Longer answers take more processing time and can use more 9-second units.
- **Can I send more than one image?**
  - No. `image` takes one image URL per request.
- **Is the 201 response from POST an error?**
  - No. 201 Created means the prediction was accepted. Use the returned `id` to poll GET `/predictions/{id}` until `status` is `succeeded`, `failed` or `canceled`.
- **What if my prediction fails?**
  - Failed predictions are not billed. Read the `error` field, check that the image URL is reachable and try again.

## Contact Us
If you have any questions or need assistance, you can reach out to us through the embedded chat on the bottom right corner of the page or send an email to hello@magicapi.com.


Caption images and answer questions about them with Meta Llama 3.2 Vision 11B: send an image URL and a prompt. $0.011 per request.