---
title: Multimodal Parsing | Developer Documentation
---

You can use a Vendor multimodal model to handle document extraction. This is more expensive than regular parsing but can get better results for some documents.

Supported models are models are [here](/llamaparse/parse/presets_and_modes/advance_parsing_modes#under-the-hood-2/index.md).

When using this mode, LlamaParse’s regular parsing is bypassed and instead the following process is used:

- A screenshot of every page of your document is taken
- Each page screenshot is sent to the multimodal with instruction to extract as `markdown`
- The resulting markdown of each page is consolidated into the final result.



## Using Multimodal mode

To use the multimodal mode, set `use_vendor_multimodal_model` to `True`. You can then select which model to use ny setting `vendor_multimodal_model_name` to the model you want to target (eg: `anthropic-sonnet-3.5`).

- [Python](#tab-panel-457)
- [API](#tab-panel-458)

```
parser = LlamaParse(
  use_vendor_multimodal_model=True,
  vendor_multimodal_model_name="anthropic-sonnet-3.5"
)
```

Terminal window

```
curl -X 'POST' \
  'https://api.cloud.llamaindex.ai/api/v1/parsing/upload'  \
  -H 'accept: application/json' \
  -H 'Content-Type: multipart/form-data' \
  -H "Authorization: Bearer $LLAMA_CLOUD_API_KEY" \
  --form 'use_vendor_multimodal_model=True' \
  --form 'vendor_multimodal_model_name="anthropic-sonnet-3.5"' \
  -F 'file=@/path/to/your/file.pdf;type=application/pdf'
```



## Bring your own LLM key (Optional)

When using To use the multimodal mode, you can supply your own vendor key to parse the document. If you choose to do so LlamaParse will only charge you 1 credit (0.3c) per page.

Using your own API key will incur some price from your model provider, and could led to fail page/document if you do not have high usage limits.

To use your own API key set the parameter `vendor_multimodal_api_key` to your own key value.

- [Python](#tab-panel-459)
- [API](#tab-panel-460)

```
parser = LlamaParse(
  parse_mode="parse_page_with_lvm",
  model="openai-gpt4o",
  vendor_multimodal_api_key="sk-proj-xxxxxx"
)
```

Terminal window

```
curl -X 'POST' \
  'https://api.cloud.llamaindex.ai/api/v1/parsing/upload'  \
  -H 'accept: application/json' \
  -H 'Content-Type: multipart/form-data' \
  -H "Authorization: Bearer $LLAMA_CLOUD_API_KEY" \
  --form 'parse_mode="parse_page_with_lvm"' \
  --form 'model="openai-gpt4o"' \
  --form 'vendor_multimodal_api_key="sk-proj-xxxxxx"' \
  -F 'file=@/path/to/your/file.pdf;type=application/pdf'
```



Note on Gemini model in EU SAAS: In our EU SAAS you need to provide a vertex AI certificate (as a string), for a valid project in europe-west1 google region.

## Custom Azure Model

You also have the possibility to use your own Azure Model Deployment using the following parameters:

- [Python](#tab-panel-461)
- [API](#tab-panel-462)

```
parser = LlamaParse(
  use_vendor_multimodal_model=True,
  azure_openai_deployment_name="llamaparse-gpt-4o",
  azure_openai_endpoint="https://<org>.openai.azure.com/openai/deployments/<dep>/chat/completions?api-version=<ver>",
  azure_openai_api_version="2024-02-15-preview",
  azure_openai_key="xxx"
)
```

Terminal window

```
curl -X 'POST' \
  'https://api.cloud.llamaindex.ai/api/v1/parsing/upload'  \
  -H 'accept: application/json' \
  -H 'Content-Type: multipart/form-data' \
  -H "Authorization: Bearer $LLAMA_CLOUD_API_KEY" \
  --form 'use_vendor_multimodal_model="true"' \
  --form 'azure_openai_deployment_name="llamaparse-gpt-4o"' \
  --form 'azure_openai_endpoint="https://<org>.openai.azure.com/openai/deployments/<dep>/chat/completions?api-version=<ver>"' \
  --form 'azure_openai_api_version="2024-02-15-preview"' \
  --form 'azure_openai_key="xxx"' \
  -F 'file=@/path/to/your/file.pdf;type=application/pdf'
```



---



## GPt4-o mode (Deprecated)

By Setting `gpt4o_mode` to `True` LlamaParse will use openAI GPT4-o to do the document reconstruction. This is still working, but we recommend using `use_vendor_multimodal_model` to `True` and `vendor_multimodal_model_name` to `openai-gpt4o` instead.

The parameter `gpt4o_api_key` is still working but we recommend using the parameter `vendor_multimodal_api_key` instead.