Vision Models ↗

    from fireworks import Fireworks

    client = Fireworks()

    response = client.chat.completions.create(
        model="accounts/fireworks/models/kimi-k2p5",
        messages=[
            {
                "role": "user",
                "content": [
                    {"type": "text", "text": "Can you describe this image?"},
                    {
                        "type": "image_url",
                        "image_url": {
                            "url": "https://images.unsplash.com/photo-1582538885592-e70a5d7ab3d3?w=800"
                        }
                    }
                ]
            }
        ]
    )

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

<span class="callout-start" data-callout-type="tip"></span>
  You can also use the [OpenAI SDK](/tools-sdks/openai-compatibility) with Fireworks by changing the base URL and API key.
<span class="callout-end"></span>
  <span class="tab-end"></span>

  <span class="tab-start" data-tab-title="JavaScript"></span>
```javascript
    import OpenAI from "openai";

    const client = new OpenAI({
      apiKey: process.env.FIREWORKS_API_KEY,
      baseURL: "https://api.fireworks.ai/inference/v1",
    });

    const response = await client.chat.completions.create({
      model: "accounts/fireworks/models/kimi-k2p5",
      messages: [
        {
          role: "user",
          content: [
            { type: "text", text: "Can you describe this image?" },
            {
              type: "image_url",
              image_url: {
                url: "https://images.unsplash.com/photo-1582538885592-e70a5d7ab3d3?w=800"
              }
            }
          ]
        }
      ]
    });

    console.log(response.choices[0].message.content);
    ```
  <span class="tab-end"></span>

  <span class="tab-start" data-tab-title="curl"></span>
```bash
    curl https://api.fireworks.ai/inference/v1/chat/completions \
      -H "Content-Type: application/json" \
      -H "Authorization: Bearer $FIREWORKS_API_KEY" \
      -d '{
        "model": "accounts/fireworks/models/kimi-k2p5",
        "messages": [
          {
            "role": "user",
            "content": [
              {"type": "text", "text": "Can you describe this image?"},
              {
                "type": "image_url",
                "image_url": {
                  "url": "https://images.unsplash.com/photo-1582538885592-e70a5d7ab3d3?w=800"
                }
              }
            ]
          }
        ]
      }'
    ```
  <span class="tab-end"></span>
<span class="tab-group-end"></span>

### Using base64-encoded images

For local files, encode them as base64 with the appropriate MIME type prefix:

<span class="tab-group-start"></span>
  <span class="tab-start" data-tab-title="Python"></span>
```python
    import base64
    from fireworks import Fireworks

    def encode_image(image_path):
        with open(image_path, "rb") as image_file:
            return base64.b64encode(image_file.read()).decode("utf-8")

    image_base64 = encode_image("your_image.jpg")

    client = Fireworks()

    response = client.chat.completions.create(
        model="accounts/fireworks/models/kimi-k2p5",
        messages=[
            {
                "role": "user",
                "content": [
                    {"type": "text", "text": "Can you describe this image?"},
                    {
                        "type": "image_url",
                        "image_url": {
                            "url": f"data:image/jpeg;base64,{image_base64}"
                        }
                    }
                ]
            }
        ]
    )

    print(response.choices[0].message.content)
    ```
  <span class="tab-end"></span>

  <span class="tab-start" data-tab-title="JavaScript"></span>
```javascript
    import OpenAI from "openai";
    import fs from "fs";

    const client = new OpenAI({
      apiKey: process.env.FIREWORKS_API_KEY,
      baseURL: "https://api.fireworks.ai/inference/v1",
    });

    const imageBase64 = fs.readFileSync("your_image.jpg").toString("base64");

    const response = await client.chat.completions.create({
      model: "accounts/fireworks/models/kimi-k2p5",
      messages: [
        {
          role: "user",
          content: [
            { type: "text", text: "Can you describe this image?" },
            {
              type: "image_url",
              image_url: {
                url: `data:image/jpeg;base64,${imageBase64}`
              }
            }
          ]
        }
      ]
    });

    console.log(response.choices[0].message.content);
    ```
  <span class="tab-end"></span>
<span class="tab-group-end"></span>

## Working with images

Vision-language models support [prompt caching](/guides/prompt-caching) to improve performance for requests with repeated content. Both text and image portions can benefit from caching to reduce time to first token by up to 80%.

**Tips for optimal performance:**

* **Use URLs for long conversations** – Reduces latency compared to base64 encoding
* **Downsize images** – Smaller images use fewer tokens and process faster
* **Structure prompts for caching** – Place static instructions at the beginning, variable content at the end
* **Include metadata in prompts** – Add context about the image directly in your text prompt

## Working with PDFs

VLMs do not natively accept PDF files as input. To analyze PDF documents, convert each page to an image and pass the images to the model using base64 encoding.

<span class="callout-start" data-callout-type="note"></span>
  Remember the [30-image limit per request](#known-limitations). For long documents, process pages in batches or select only the relevant pages.
<span class="callout-end"></span>

<span class="tab-group-start"></span>
  <span class="tab-start" data-tab-title="Python"></span>
Install [PyMuPDF](https://pymupdf.readthedocs.io/):

```bash
    pip install pymupdf fireworks-ai
    ```

```python
    import base64
    import fitz
    from fireworks.client import Fireworks


    def pdf_pages_to_base64(pdf_path, dpi=200):
        doc = fitz.open(pdf_path)
        images = []
        for page in doc:
            pix = page.get_pixmap(dpi=dpi)
            images.append(base64.b64encode(pix.tobytes("png")).decode("utf-8"))
        doc.close()
        return images


    page_images = pdf_pages_to_base64("document.pdf")

    client = Fireworks()

    content = [{"type": "text", "text": "Summarize this document."}]
    for img in page_images:
        content.append({
            "type": "image_url",
            "image_url": {"url": f"data:image/png;base64,{img}"}
        })

    response = client.chat.completions.create(
        model="accounts/fireworks/models/kimi-k2p5",
        messages=[{"role": "user", "content": content}]
    )

    print(response.choices[0].message.content)
    ```
  <span class="tab-end"></span>

  <span class="tab-start" data-tab-title="JavaScript"></span>
Install [pdf-to-img](https://www.npmjs.com/package/pdf-to-img) and [openai](https://www.npmjs.com/package/openai):

```bash
    npm install pdf-to-img openai
    ```

```javascript
    import { pdf } from "pdf-to-img";
    import OpenAI from "openai";

    const client = new OpenAI({
      apiKey: process.env.FIREWORKS_API_KEY,
      baseURL: "https://api.fireworks.ai/inference/v1",
    });

    const pages = [];
    for await (const page of await pdf("document.pdf", { scale: 2.0 })) {
      pages.push(Buffer.from(page).toString("base64"));
    }

    const content = [
      { type: "text", text: "Summarize this document." },
      ...pages.map((base64) => ({
        type: "image_url",
        image_url: { url: `data:image/png;base64,${base64}` },
      })),
    ];

    const response = await client.chat.completions.create({
      model: "accounts/fireworks/models/kimi-k2p5",
      messages: [{ role: "user", content }],
    });

    console.log(response.choices[0].message.content);
    ```
  <span class="tab-end"></span>
<span class="tab-group-end"></span>

## Advanced capabilities

<span class="card-group-start" data-cols="2"></span>
  <span class="card-start" data-card-title="Vision fine-tuning" data-card-href="/fine-tuning/fine-tuning-vlm"></span>
Fine-tune VLMs for specialized visual tasks
  <span class="card-end"></span>

  <span class="card-start" data-card-title="LoRA adapters" data-card-href="/models/uploading-custom-models"></span>
Deploy custom LoRA adapters for vision models
  <span class="card-end"></span>

  <span class="card-start" data-card-title="Dedicated deployments" data-card-href="/getting-started/ondemand-quickstart"></span>
Deploy VLMs on dedicated GPUs for better performance
  <span class="card-end"></span>

  <span class="card-start" data-card-title="Video & audio inputs" data-card-href="/guides/video-audio-inputs"></span>
Process video and audio content with multimodal models
  <span class="card-end"></span>
<span class="card-group-end"></span>

## Alternative query methods

For the Completions API, manually insert the image token `<image>` in your prompt and supply images as an ordered list:

```python
response = client.completions.create(
    model="accounts/fireworks/models/kimi-k2p5",
    prompt="SYSTEM: Hello\n\nUSER:<image>\ntell me about the image\n\nASSISTANT:",
    extra_body={
        "images": ["https://images.unsplash.com/photo-1582538885592-e70a5d7ab3d3?ixlib=rb-4.0.3&ixid=M3wxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8fA%3D%3D&auto=format&fit=crop&w=1770&q=80"]
    }
)

print(response.choices[0].text)