> ## Documentation Index
> Fetch the complete documentation index at: https://docs.vlm.run/llms.txt
> Use this file to discover all available pages before exploring further.
# Multimodal Inputs
> Content part types, per-modality limits, and format tradeoffs
Content parts are supplied under `messages[].content`, following the same
shape OpenAI's SDKs already use. Each part is one of:
| Part | Accepts | Notes |
| -------------- | ----------------------------------- | ------------------------------------------------------------------- |
| `text` | Plain text | Prompt or question text. |
| `image_url` | `url` or base64 data URI | Single image per request for OCR models; VQA models accept multiple |
| `document_url` | `url`, file URL, or base64 data URI | PDF; enters the page-wise document pipeline |
The VLM Run Gateway validates content parts against each model's capabilities before
inference. Mismatches return `400` with
[`capability_violation`](/gateway/error-codes#capability-violation-400). Check
a model's accepted input types on [Models](/gateway/models) or
[`GET /v1/openai/models`](/gateway/api-reference/get-models).
## Image Inputs
Most OCR and vision models accept a single `image_url` part per request. VQA
models such as `qwen/qwen3.5-0.8b` accept multiple images in the same
message, for side-by-side comparison or multi-image context.
```json theme={"theme":{"light":"github-light","dark":"dark-plus"}}
{
"type": "image_url",
"image_url": { "url": "https://example.com/photo.jpg" }
}
```
Use `image_resolution` to resize an image before inference when a model's
default resolution costs more than the task needs. See
[Gateway extensions](/gateway/api-reference/post-chat-completions#gateway-extensions)
for the full parameter reference.
## Document Inputs
Document (PDF) requests are decoded and rasterized at the ingress before
per-page inference.
### Limits
| Limit | Value | Notes |
| --------- | -------------------------- | --------------------------------------------------------- |
| File size | 100 MB | Enforced before decoding starts. |
| Pages | 500 (`document_max_pages`) | Requests exceeding the cap are rejected before inference. |
Requests over either limit return `400` with `error.code = "invalid_document"`.
See [Error Codes](/gateway/error-codes#invalid-document-400).
### URL vs. base64
| Input | Use when |
| -------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------- |
| `document_url` with a hosted URL | Default choice; keeps the request body small and fast to transmit. |
| Base64 data URI | Only when the document isn't already hosted somewhere reachable. Inflates the request body by \~33% and increases request latency for large files. |
```json theme={"theme":{"light":"github-light","dark":"dark-plus"}}
{
"type": "document_url",
"document_url": { "url": "https://example.com/report.pdf" }
}
```
Prefer a URL over base64 whenever possible, especially for documents over a
few megabytes.
For `document_dpi` and other method-specific knobs, see
[Method Parameters](/gateway/methods#method-parameters).
### Scanned vs. native PDFs
The VLM Run Gateway rasterizes every page and runs OCR regardless of whether the
source PDF has a text layer. Scanned (image-only) and native (text-layer)
PDFs are handled the same way, both go through the OCR model rather than a
text-extraction shortcut. If you already have a reliable text layer and
don't need OCR, extracting it client-side before calling the Gateway will be
faster and cheaper.
## Related
End-to-end recipe from model selection to response parsing.
Receive pages as they finish instead of waiting for the whole document.
Which input types each model accepts.
Full request and response schema.